© 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. 49161
    Prev
    Next
    INDEX
    Explanations

    unto the, has chosen, alpine-devel, Everest

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

    document subjects and titles

    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
    ात्
    0.47
    even
    0.46
    ه
    0.45
    ה
    0.42
    este
    0.41
    <0x9D>
    0.41
    েও
    0.41
    ovor
    0.41
    urar
    0.41
    ului
    0.40
    POSITIVE LOGITS
     Fellowship
    0.49
     ヒ
    0.49
     ሁ
    0.49
     ISZ
    0.49
     Collegiate
    0.48
     Thee
    0.48
     อย
    0.48
     Expr
    0.47
     丿
    0.47
     Gölü
    0.47
    Activations Density 0.000%

    No Known Activations