© 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. 78162
    Prev
    Next
    INDEX
    Explanations

    know enough

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

    abstract nouns or specific conditions

    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
     disenfranch
    0.44
     Drinfeld
    0.44
     육
    0.43
     αυτό
    0.43
     Barbosa
    0.43
     ایک
    0.42
    ímenes
    0.42
     שא
    0.41
    ífer
    0.41
     منسلک
    0.41
    POSITIVE LOGITS
    els
    0.44
    LOT
    0.43
    ジャ
    0.43
    ELS
    0.42
    V
    0.41
                       
    0.41
    вет
    0.41
    或其他
    0.41
    勉強
    0.40
    VID
    0.40
    Activations Density 0.000%

    No Known Activations