© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152531
    Prev
    Next
    INDEX
    Explanations

    2 drawer file cabinets

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

    finance, code, or terms after punctuation

    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
    С
    0.60
    ス
    0.57
    SZ
    0.56
    ס
    0.53
    ЗА
    0.52
    י
    0.52
    nobody
    0.51
    스
    0.51
    З
    0.50
    О
    0.50
    POSITIVE LOGITS
    ^{-
    0.48
     Fundraising
    0.48
     स्रो
    0.46
     मुख्यतः
    0.45
     journal
    0.44
     ripening
    0.44
     retrieving
    0.44
     inhibits
    0.44
     demonstrates
    0.44
     detalle
    0.44
    Activations Density 0.000%

    No Known Activations