© 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. 26343
    Prev
    Next
    INDEX
    Explanations

    assorted types

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

    checks, forecast,Nintendo, Bot, ChatGPT, time

    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
     तब
    0.49
    á
    0.49
     ढ
    0.47
    rij
    0.47
    蒇
    0.46
     fors
    0.46
     अनुसूचित
    0.45
     temperatur
    0.45
     ป
    0.45
    uded
    0.45
    POSITIVE LOGITS
    ডার
    0.48
     afforded
    0.47
     Elovl
    0.46
     vacuoles
    0.46
    得到了
    0.45
     gosto
    0.45
    لوب
    0.45
    ન્યા
    0.44
    োর্
    0.43
    রু
    0.42
    Activations Density 0.000%

    No Known Activations