© 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. 142093
    Prev
    Next
    INDEX
    Explanations

    countries, regions, languages

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

    Base temperature, academically accepted, within acceptable

    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
    _
    0.64
    /
    0.63
     at
    0.57
    :
    0.57
    ł
    0.57
    el
    0.55
    ;
    0.55
    f
    0.53
    .
    0.50
    -
    0.50
    POSITIVE LOGITS
    國
    0.46
    vaegir
    0.45
     インド
    0.44
     ቫ
    0.44
     डोंगर
    0.43
    ジュ
    0.43
    国の
    0.43
     टेंपरेचर
    0.43
    瞌
    0.42
     abrang
    0.41
    Activations Density 0.000%

    No Known Activations