© 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. 169828
    Prev
    Next
    INDEX
    Explanations

    domicile, caution, torque

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

    harmful or prohibited content involving minors

    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
     zählt
    0.48
     zählen
    0.47
    ม
    0.46
     งาน
    0.44
    .’
    0.44
     può
    0.43
     formatting
    0.43
     MCC
    0.43
     postseason
    0.43
     उपयोगी
    0.43
    POSITIVE LOGITS
    検査
    0.48
    外部
    0.47
     memeriksa
    0.46
    едера
    0.46
    긱
    0.45
    ヒト
    0.45
    classical
    0.45
     swoim
    0.45
    CLUDED
    0.45
    自分で
    0.44
    Activations Density 0.000%

    No Known Activations