© 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. 191961
    Prev
    Next
    INDEX
    Explanations

    business serves Asian

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

    durability or duration

    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
     برضو
    0.58
    Todos
    0.54
     الدهون
    0.50
    getClient
    0.50
    Aprend
    0.50
     veröffentlicht
    0.49
    愴
    0.48
     কাপড়
    0.47
    otherapie
    0.46
    Even
    0.46
    POSITIVE LOGITS
    のみ
    0.49
    ו
    0.48
    从事
    0.46
    യെ
    0.45
    व
    0.44
    グ
    0.43
     "_"
    0.43
    掣
    0.43
     defeats
    0.43
     ઉ
    0.42
    Activations Density 0.000%

    No Known Activations