© 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. 40786
    Prev
    Next
    INDEX
    Explanations

    sexually immoral product features

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

    storing cryptography breath without

    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
    畊
    0.43
     турни
    0.43
    足
    0.43
    푐
    0.42
    口味
    0.42
    켤
    0.42
    GH
    0.41
    烹
    0.41
     반려
    0.40
     бел
    0.39
    POSITIVE LOGITS
     threatens
    0.46
    purpose
    0.46
     Purpose
    0.44
     Autonomous
    0.43
     Biotechn
    0.42
    ›
    0.42
    !).
    0.41
     microbes
    0.41
     incentiv
    0.41
     Name
    0.40
    Activations Density 0.001%

    No Known Activations