© 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. 101762
    Prev
    Next
    INDEX
    Explanations

    new flooring

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

    response time and outcomes

    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
    놨
    0.65
    TE
    0.55
    ียบ
    0.54
    衝撃
    0.46
    ギ
    0.45
    뒀
    0.45
    weh
    0.45
    리가
    0.45
    넉
    0.44
    モード
    0.44
    POSITIVE LOGITS
     historians
    0.50
     Rhe
    0.47
     Wiltshire
    0.46
     нач
    0.46
     தோன்ற
    0.45
     ബാറ്ററി
    0.45
     осуществляется
    0.44
     Hodgson
    0.44
     recorded
    0.44
    recorded
    0.44
    Activations Density 0.003%

    No Known Activations