© 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. 179031
    Prev
    Next
    INDEX
    Explanations

    market share

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

    specific nouns and names

    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
    /*
    0.54
    ✨
    0.52
    â
    0.52
     tys
    0.50
    ‼️
    0.50
    <h5>
    0.48
    Intro
    0.48
    <h3>
    0.48
    <h4>
    0.48
    ED
    0.48
    POSITIVE LOGITS
     沒有
    0.58
     這個
    0.53
     Montevideo
    0.53
     circost
    0.52
    Colonne
    0.50
    ಧಾನ
    0.49
     چکے
    0.49
    <unused78>
    0.49
    wives
    0.48
     المنطقة
    0.48
    Activations Density 0.004%

    No Known Activations