© 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. 241922
    Prev
    Next
    INDEX
    Explanations

    staffHub, technical pearl, UX Forum

    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
    (
    0.53
    HAI
    0.49
    passive
    0.49
     feeder
    0.49
    *
    0.48
     passive
    0.48
    live
    0.46
     mansion
    0.46
     cookie
    0.46
    en
    0.46
    POSITIVE LOGITS
    ү
    0.50
    üss
    0.48
    ولوج
    0.46
     Eugène
    0.46
    磕
    0.45
    ன்ப
    0.44
    Marin
    0.44
    ûr
    0.44
    ","_
    0.43
    یکس
    0.43
    Activations Density 0.000%

    No Known Activations