© 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. 223751
    Prev
    Next
    INDEX
    Explanations

    had / has: held, known, thing, spend

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

    holding eggs

    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
     speculated
    0.52
     reported
    0.50
     rapporte
    0.48
     圆
    0.47
     artworks
    0.46
     investigated
    0.46
     inspected
    0.45
    ോളം
    0.45
     automate
    0.45
     easements
    0.45
    POSITIVE LOGITS
    寒い
    0.54
    به
    0.52
    外面
    0.50
    aunque
    0.50
    蕞
    0.50
    乍
    0.49
    evident
    0.49
    Formula
    0.49
    原本
    0.48
    ਦੇ
    0.48
    Activations Density 0.000%

    No Known Activations