© 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. 245993
    Prev
    Next
    INDEX
    Explanations

    starting with common words

    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
    蜮
    0.54
    <unused1012>
    0.52
    abhavam
    0.52
    <unused204>
    0.50
     überprüft
    0.50
     कोविड
    0.49
    ünstler
    0.48
     जलवायु
    0.48
    BUGFS
    0.47
     долларов
    0.47
    POSITIVE LOGITS
    <html>
    0.45
    LINES
    0.44
    ੋ
    0.44
    HALL
    0.44
    g
    0.44
    سط
    0.43
    Circle
    0.43
    ونة
    0.43
    ذ
    0.43
    gore
    0.43
    Activations Density 0.000%

    No Known Activations