© 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. 195844
    Prev
    Next
    INDEX
    Explanations

    coin directly, refill tools, framing one

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

    harmful ethical considerations of fictional depictions

    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
    었는데
    0.47
    훼
    0.46
    elere
    0.46
     할인
    0.45
    踝
    0.45
     은행
    0.44
     ഇന്ത്യൻ
    0.44
     ಭಾರತ
    0.44
     giày
    0.44
     הז
    0.43
    POSITIVE LOGITS
     implementations
    0.40
    س
    0.39
     standalone
    0.39
    بوع
    0.39
     Properly
    0.39
    سل
    0.37
    تب
    0.37
     –
    0.37
     purposes
    0.37
     burners
    0.37
    Activations Density 0.001%

    No Known Activations