© 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. 83581
    Prev
    Next
    INDEX
    Explanations

    teaching classes, real business

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

    project of the Name

    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
    CIÓN
    0.43
     ($
    0.42
     बढ़ते
    0.42
    словия
    0.42
    }{*}{
    0.42
    ście
    0.41
     স্বাধীন
    0.41
     WndProc
    0.41
    čku
    0.40
     مکان
    0.40
    POSITIVE LOGITS
     المثلثيه
    0.45
     heißt
    0.44
    抧
    0.44
    䔬
    0.44
     ء
    0.43
     نار
    0.43
    onha
    0.42
    ولد
    0.42
    eternal
    0.42
     እየሱስ
    0.41
    Activations Density 0.002%

    No Known Activations