© 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. 155234
    Prev
    Next
    INDEX
    Explanations

    tradition and customs

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

    disagreements and legal cases

    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
    領域
    0.47
    駕駛
    0.43
    ᡳ
    0.43
    AMAN
    0.42
     სხვა
    0.42
     ！
    0.42
    餘
    0.42
    許多
    0.41
    ᠰ
    0.40
    羹
    0.40
    POSITIVE LOGITS
     tradiciones
    0.46
     tradizione
    0.46
     tradición
    0.46
    jit
    0.46
     evidencias
    0.44
     धूमधाम
    0.44
     પાર
    0.44
    case
    0.43
     Import
    0.43
     Autor
    0.42
    Activations Density 0.001%

    No Known Activations