© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 65608
    Prev
    Next
    INDEX
    Explanations

    free, reviews, attacks

    np_acts-logits-general · gemini-2.5-flash-lite

    naming something or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ение
    0.49
    rschein
    0.47
    м
    0.46
    nouns
    0.45
    ary
    0.43
     เอา
    0.43
    ії
    0.43
    厠
    0.43
    ünüz
    0.42
    aries
    0.42
    POSITIVE LOGITS
     இறுதி
    0.51
     Vaughn
    0.48
    시는
    0.45
    {:
    0.43
     അത
    0.42
     면
    0.42
     учетом
    0.42
    ർട്ട
    0.42
    leda
    0.41
     Clement
    0.40
    Activations Density 0.001%

    No Known Activations