© 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. 97590
    Prev
    Next
    INDEX
    Explanations

    servicesmeetingwaswas

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

    Virtual, later, pizza, week, restriction

    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
    过去
    0.50
    確定
    0.50
    䢎
    0.48
    片段
    0.45
    過去
    0.45
     Shor
    0.45
    量を
    0.45
    鈕
    0.44
    ালার
    0.44
    開始
    0.43
    POSITIVE LOGITS
     carcinomas
    0.45
    u
    0.44
     explica
    0.44
     aficionados
    0.44
    疖
    0.43
    os
    0.42
    o
    0.42
     enfermo
    0.42
    LAN
    0.42
     solicitar
    0.41
    Activations Density 0.000%

    No Known Activations