© 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. 235050
    Prev
    Next
    INDEX
    Explanations

    considering the, close family

    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
     الأع
    0.56
    PHIA
    0.51
     どれ
    0.49
     أنها
    0.46
    是用
    0.46
     低
    0.46
    ناها
    0.46
     例如
    0.46
    ANIA
    0.45
    和他
    0.44
    POSITIVE LOGITS
     Iran
    0.55
    трон
    0.54
    direita
    0.51
    concurrent
    0.47
    <
    0.46
    [
    0.45
    тро
    0.45
     civilizations
    0.44
     Iranian
    0.44
    यण
    0.44
    Activations Density 0.000%

    No Known Activations