© 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. 108957
    Prev
    Next
    INDEX
    Explanations

    arty boy

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

    financial concepts for assistance

    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
    وير
    0.46
     Angeb
    0.45
    ції
    0.44
     contaminated
    0.44
    踽
    0.44
     Edmond
    0.43
     rainwater
    0.43
     Einen
    0.43
    قوم
    0.43
    شارة
    0.43
    POSITIVE LOGITS
    $，
    0.52
    䉿
    0.47
    撚
    0.46
     ಏಕೆ
    0.45
    financ
    0.45
     є
    0.45
    avía
    0.44
     делается
    0.44
     ネックレス
    0.43
     prolet
    0.43
    Activations Density 0.000%

    No Known Activations