© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8970
    Prev
    Next
    INDEX
    Explanations

    user<MAX_ACTIVATING_TOKENS>..........</MAX_ACTIVATING_TOKENS><TOKENS_AFTER_MAX_ACTIVATING_TOKEN>1987200519901996200619891992199419931995</TOKENS_AFTER_MAX_ACTIVATING_TOKEN><TOP_POSITIVE_LOGITS>1990198919931987199419911988200619952008</TOP_POSITIVE_LOGITS><TOP_ACTIVATING_TEXTS>He was born in 1987.In London in 1990.I mean I'm not happy that I'm spending my time for 2005.I'm sure there was a chance for 1996.A long time ago, a person from 2006.How about 1989? Can we have that?She was born 1992.I've been here since 1994.He died in 1993.He was born in 1995.</TOP_ACTIVATING_TEXTS>Explain the neuron above with a word or phrase, not a complete sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     équipe
    0.38
     αυτό
    0.35
     generalizes
    0.34
     resizing
    0.34
    Если
    0.34
    ใช่
    0.34
     avec
    0.33
    这
    0.33
    If
    0.32
     நானும்
    0.32
    POSITIVE LOGITS
    leigh
    0.32
     Wiggins
    0.27
    ಎಂ
    0.27
    rlige
    0.27
    Belle
    0.27
    stl
    0.26
    asc
    0.26
    mathbf
    0.26
    వి
    0.26
    greencar
    0.26
    Activations Density 0.001%

    No Known Activations