© 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. 15889
    Prev
    Next
    INDEX
    Explanations

    asterisks and specific words

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

    `/*`

    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
    >
    0.94
    <0x80>
    0.92
     necesito
    0.73
    ли
    0.71
    شي
    0.70
    ból
    0.70
    olí
    0.70
    ل
    0.70
    기
    0.69
     anunci
    0.67
    POSITIVE LOGITS
     in
    0.71
     for
    0.60
    ua
    0.60
    do
    0.58
    tem
    0.58
    tim
    0.58
     are
    0.58
    cough
    0.58
    z
    0.58
    sigh
    0.57
    Activations Density 0.018%

    No Known Activations