© 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. 79691
    Prev
    Next
    INDEX
    Explanations

    compound nouns and phrases

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

    specific details and instructions

    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
    IN
    0.70
    AR
    0.59
    WI
    0.59
    IR
    0.53
    au
    0.52
    FT
    0.52
    OD
    0.52
    6
    0.51
    NOT
    0.50
    OR
    0.50
    POSITIVE LOGITS
     ორგან
    0.52
    aderie
    0.46
    ゞ
    0.46
     незавершена
    0.46
    უშა
    0.44
    申し上げ
    0.44
    тую
    0.44
    ią
    0.43
    客様
    0.43
    ：“
    0.42
    Activations Density 0.000%

    No Known Activations