© 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-16K
    7. 12200
    Prev
    Next
    INDEX
    Explanations

    re: discussion subjects

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

    surface of

    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_16k_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
    that
    0.53
    as
    0.53
    rule
    0.52
    и
    0.52
    in
    0.51
    имо
    0.50
    to
    0.49
    surprisingly
    0.49
    but
    0.48
    chets
    0.48
    POSITIVE LOGITS
     নগর
    0.49
     Montevideo
    0.48
     CELL
    0.45
    させる
    0.44
     RIVER
    0.43
    +%
    0.43
     raids
    0.43
    ”、
    0.42
     カー
    0.42
     STAFF
    0.41
    Activations Density 0.001%

    No Known Activations