© 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. 147713
    Prev
    Next
    INDEX
    Explanations

    teen drivers

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

    resolve dissonance or reveal information

    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
     Surplus
    0.53
     a
    0.53
     Jer
    0.52
     VISA
    0.49
     Arabic
    0.49
    ા
    0.48
    ל
    0.48
    jadi
    0.48
     Daf
    0.46
    தி
    0.46
    POSITIVE LOGITS
    '،
    0.46
    ،
    0.45
    IGet
    0.44
    utzen
    0.44
    ONEDB
    0.43
     বিকেলে
    0.42
    ECUTIVE
    0.42
    뮤
    0.42
    entown
    0.42
    resolvers
    0.41
    Activations Density 0.000%

    No Known Activations