© 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. 198468
    Prev
    Next
    INDEX
    Explanations

    chat roomVPN andcourse feefiat specsopens toimpulsive activitiesread MiamiCEO ofhair and" Standard

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

    germinate

    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
    чность
    0.59
    iciência
    0.57
     非常
    0.53
     事
    0.50
    ках
    0.49
     带
    0.49
    一枚
    0.48
     critères
    0.47
    чности
    0.47
    ividade
    0.46
    POSITIVE LOGITS
     additional
    0.49
     supplementary
    0.48
    okon
    0.48
     oral
    0.46
    umer
    0.45
     peoples
    0.45
    었
    0.45
    oral
    0.45
    ർ
    0.45
     esto
    0.45
    Activations Density 0.003%

    No Known Activations