© 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. 249204
    Prev
    Next
    INDEX
    Explanations

    listing data

    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
     соору
    0.47
     सांप
    0.47
    啸
    0.46
    ÖR
    0.46
     गाड़ी
    0.46
    逶
    0.46
     кеңсесинде
    0.45
     Clas
    0.44
    ໂຕ
    0.44
    kében
    0.44
    POSITIVE LOGITS
     nota
    0.43
    ブルー
    0.43
    raff
    0.43
     correct
    0.43
    長期
    0.42
     clínicos
    0.42
    且
    0.42
     &&
    0.42
    null
    0.41
    描
    0.41
    Activations Density 0.000%

    No Known Activations