© 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. 100104
    Prev
    Next
    INDEX
    Explanations

    plan organizer

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

    inciting violence

    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
    újo
    0.50
    有问题
    0.47
     Probleme
    0.46
    ״
    0.46
    系の
    0.45
     değildir
    0.45
     വ്യത്യസ്ത
    0.44
     Góc
    0.43
    一定会
    0.43
    都不会
    0.43
    POSITIVE LOGITS
     up
    0.47
     shopper
    0.47
     shopping
    0.47
     t
    0.47
     shoppers
    0.45
     OL
    0.45
    <0xE3>
    0.44
     int
    0.43
     о
    0.43
    าร
    0.43
    Activations Density 0.000%

    No Known Activations