© 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. 135561
    Prev
    Next
    INDEX
    Explanations

    certification, future, Walking Dead

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

    capped-profit, Runner, accepted, card

    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
     Medical
    0.45
     Miscellaneous
    0.45
    árs
    0.45
     Surprisingly
    0.44
    1
    0.44
    ủ
    0.43
     Sox
    0.43
    NERS
    0.43
    ap
    0.43
    ip
    0.43
    POSITIVE LOGITS
    จะได้
    0.49
    烔
    0.47
    lte
    0.46
     infrastrukt
    0.46
    DebugTest
    0.46
     삼성
    0.46
    Wer
    0.46
     betray
    0.46
    视野
    0.45
    樎
    0.45
    Activations Density 0.001%

    No Known Activations