© 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. 202330
    Prev
    Next
    INDEX
    Explanations

    domain specific management

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

    enumeration or completion

    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
    uene
    0.52
    ЕЛЬ
    0.45
    其他人
    0.45
    ้น
    0.44
     නැ
    0.43
     pennies
    0.42
     signifikan
    0.42
    u
    0.41
    ьому
    0.40
     *>
    0.40
    POSITIVE LOGITS
     ಬೆಳ
    0.47
     Yosh
    0.47
    comm
    0.46
     કર્મચારી
    0.46
    Yosh
    0.45
    MX
    0.44
     הי
    0.44
     disclosures
    0.44
    ngày
    0.43
    vert
    0.43
    Activations Density 0.000%

    No Known Activations