© 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. 64616
    Prev
    Next
    INDEX
    Explanations

    pros and contras

    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
    িগ্ন
    0.50
     lanterns
    0.45
    ိန်
    0.44
    ্লেখ
    0.44
    ಿಕೆ
    0.44
    蚓
    0.43
     Ignition
    0.43
    眄
    0.43
    ब्दी
    0.42
     légère
    0.42
    POSITIVE LOGITS
    azo
    0.50
    ayo
    0.49
    aces
    0.46
     десятки
    0.46
    udad
    0.45
    buster
    0.45
    <0xEC>
    0.44
     مراکز
    0.44
    aya
    0.43
    ayan
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.