© 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. 85625
    Prev
    Next
    INDEX
    Explanations

    Article, Blog, applicable

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

    dark social, errors, and abbreviations

    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
     большое
    0.53
    მას
    0.48
    geht
    0.48
     مارس
    0.46
     rapproche
    0.46
    盔
    0.45
     März
    0.45
    concatenate
    0.45
    他說
    0.44
     огромное
    0.44
    POSITIVE LOGITS
     sj
    0.49
     semi
    0.44
     sem
    0.44
    Awesome
    0.43
     bar
    0.43
     sint
    0.43
    š
    0.43
     jug
    0.43
     kap
    0.43
    Soul
    0.43
    Activations Density 0.000%

    No Known Activations