© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1595
    Prev
    Next
    INDEX
    Explanations

    javascript code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    streetlight
    0.46
    HOBBIT
    0.43
    鰓
    0.42
    টিশ
    0.42
    䧺
    0.42
    👙
    0.41
    📪
    0.41
    setFixedHeight
    0.40
     මිනි
    0.39
    🔳
    0.39
    POSITIVE LOGITS
     _
    0.60
    Object
    0.52
     t
    0.50
    void
    0.50
    exports
    0.50
     (_
    0.48
     void
    0.48
    (_
    0.48
    e
    0.48
    var
    0.47
    Activations Density 0.001%

    No Known Activations