© 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. 229763
    Prev
    Next
    INDEX
    Explanations

    biological pathways

    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
     архі
    0.61
    𒌋
    0.58
     Владимир
    0.57
     წინ
    0.57
    |।
    0.56
    тории
    0.56
     предше
    0.56
    aliśmy
    0.56
    檤
    0.56
     questão
    0.54
    POSITIVE LOGITS
    0.81
    /
    0.55
    (
    0.53
    </h3>
    0.52
     brightness
    0.51
     ionic
    0.50
     ions
    0.49
    -
    0.49
    ↵
    0.49
     weighted
    0.49
    Activations Density 0.000%

    No Known Activations