© 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. 50827
    Prev
    Next
    INDEX
    Explanations

    protect against

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

    multilingual list item descriptions

    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
    рио
    0.50
    тный
    0.49
    ем
    0.49
     compatible
    0.48
     работает
    0.47
     favoured
    0.47
    _
    0.47
     values
    0.46
    profiss
    0.46
    ટક
    0.46
    POSITIVE LOGITS
     അദ്ദേഹ
    0.54
     ztr
    0.52
     Nghi
    0.49
    sled
    0.49
     dém
    0.48
    CLOS
    0.48
     {}>,
    0.47
     därför
    0.47
     lbs
    0.46
     ඉද
    0.46
    Activations Density 0.000%

    No Known Activations