© 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. 72940
    Prev
    Next
    INDEX
    Explanations

    instructions, specific groups, or emphasis

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

    African perspective or screenplay formatting

    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
    Undo
    0.55
     постара
    0.53
    ANGMAR
    0.52
     решать
    0.52
     고민
    0.52
     સમસ્યા
    0.52
    問題を
    0.51
    ५
    0.51
     ошибок
    0.50
     стар
    0.50
    POSITIVE LOGITS
     Officials
    0.57
     Department
    0.57
     Fullerton
    0.57
     Cafe
    0.55
     module
    0.55
     Services
    0.54
     profile
    0.54
     Rece
    0.54
     Archives
    0.54
     Journal
    0.53
    Activations Density 0.000%

    No Known Activations