© 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. 245703
    Prev
    Next
    INDEX
    Explanations

    lists of items

    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
    Biggest
    0.48
    wau
    0.46
    條
    0.46
    тором
    0.44
    K
    0.44
    ської
    0.44
    W
    0.43
    PQ
    0.43
    чів
    0.43
    으
    0.43
    POSITIVE LOGITS
    ですし
    0.45
     financiera
    0.44
    ỗng
    0.44
     unaccompanied
    0.44
     retails
    0.43
     aventura
    0.43
     whimsical
    0.43
     Tuscan
    0.42
     cameos
    0.42
     arched
    0.42
    Activations Density 0.000%

    No Known Activations