© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78081
    Prev
    Next
    INDEX
    Explanations

    technical or specific terms

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

    refuse to continue harmful content

    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
    Negative Logits
    Cou
    0.51
    ρα
    0.50
    H
    0.49
    Vie
    0.47
    Radio
    0.47
    τρα
    0.47
    <0xB3>
    0.46
    rol
    0.45
    Court
    0.45
    hou
    0.45
    POSITIVE LOGITS
     município
    0.49
     Srps
    0.48
    <unused37>
    0.48
     keputusan
    0.45
    ানোর
    0.45
     mimics
    0.45
     almış
    0.45
     invito
    0.45
     gönd
    0.44
    薷
    0.44
    Activations Density 0.001%

    No Known Activations