© 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. 63076
    Prev
    Next
    INDEX
    Explanations

    financial and legal contexts

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

    OpenAPI Specification, tensor, response codes

    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
    USH
    0.54
    ل
    0.52
     on
    0.48
    н
    0.48
    ॉप
    0.47
    る
    0.45
     preside
    0.45
     il
    0.44
    एको
    0.44
     off
    0.43
    POSITIVE LOGITS
    优秀
    0.45
     البيت
    0.45
    鲷
    0.44
     类型
    0.43
     роста
    0.43
    DistanceFrom
    0.43
    自身的
    0.43
     genannten
    0.42
    ྒ
    0.42
     cest
    0.42
    Activations Density 0.000%

    No Known Activations