© 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. 114647
    Prev
    Next
    INDEX
    Explanations

    copyright © website events

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

    creating and producing data

    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
     स्टेटमेंट
    0.46
     recommendation
    0.45
     även
    0.44
    숍
    0.43
     গেলেন
    0.43
     représent
    0.43
     Monterey
    0.43
     rapporter
    0.42
    에서도
    0.42
     bygg
    0.42
    POSITIVE LOGITS
    getSeconds
    0.54
    _*
    0.54
    centroid
    0.54
    "*
    0.52
    _+
    0.51
    Κα
    0.51
     快
    0.50
    Что
    0.49
    __
    0.49
    rubber
    0.49
    Activations Density 0.000%

    No Known Activations