© 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. 85416
    Prev
    Next
    INDEX
    Explanations

    cannot demonstrate, raise awareness

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

    starts and explanations

    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
    Negative Logits
    逦
    0.53
    icions
    0.52
     contender
    0.50
    Bristol
    0.47
    Properties
    0.46
    ኵ
    0.46
    ியும்
    0.46
    浲
    0.43
    Cake
    0.43
    ornis
    0.43
    POSITIVE LOGITS
     $)
    0.48
     economists
    0.47
     істо
    0.47
     ECONOMIC
    0.46
    NAMEN
    0.44
     economist
    0.43
    COME
    0.43
     معين
    0.42
     dollars
    0.42
     ⿻
    0.42
    Activations Density 0.001%

    No Known Activations