© 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. 9127
    Prev
    Next
    INDEX
    Explanations

    how to use

    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
    Negative Logits
    axies
    0.35
    o
    0.32
    Rf
    0.31
    avier
    0.30
    u
    0.30
    r
    0.29
    auri
    0.29
    first
    0.29
    array
    0.29
    phone
    0.29
    POSITIVE LOGITS
     the
    0.38
     its
    0.35
     kons
    0.34
     J
    0.34
     them
    0.33
     regularmente
    0.33
     with
    0.33
     this
    0.33
     another
    0.32
     yrs
    0.32
    Activations Density 0.090%

    No Known Activations