© 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. 248885
    Prev
    Next
    INDEX
    Explanations

    foreign character activation gallery

    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
    b
    0.54
    hs
    0.48
     ranked
    0.47
    appell
    0.46
     cryst
    0.46
    s
    0.46
    plic
    0.45
    apr
    0.45
    usuario
    0.44
    ethod
    0.43
    POSITIVE LOGITS
    த்திற்கு
    0.50
     ndani
    0.46
     इत्यादी
    0.46
    ᑎ
    0.46
    💴
    0.46
    នៅក្នុង
    0.46
    .”.
    0.46
    તી
    0.45
     રહ્યા
    0.45
    のではない
    0.45
    Activations Density 0.000%

    No Known Activations