© 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. 177837
    Prev
    Next
    INDEX
    Explanations

    explains how that what

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

    explaining what or why

    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
    。
    0.77
     понять
    0.75
    。,
    0.69
    。\
    0.68
     understand
    0.67
     powied
    0.66
     forstå
    0.64
    espère
    0.63
    ।,
    0.62
     interpr
    0.62
    POSITIVE LOGITS
    ك
    0.73
    ה
    0.70
    고
    0.68
    ه
    0.67
    in
    0.66
    ین
    0.66
    ב
    0.66
    드
    0.64
    ان
    0.61
    why
    0.61
    Activations Density 0.022%

    No Known Activations