© 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. 221083
    Prev
    Next
    INDEX
    Explanations

    nature, abilities, names

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

    explanation based on meaning

    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
     şeh
    0.52
    ört
    0.51
     şeyler
    0.49
     więc
    0.49
     pö
    0.48
     toată
    0.48
     おい
    0.48
     goût
    0.47
     😏
    0.47
     pă
    0.46
    POSITIVE LOGITS
    haviours
    0.47
     Novels
    0.46
    нува
    0.46
    ките
    0.45
    FP
    0.44
     Inclusive
    0.44
     Engaging
    0.43
    居家
    0.43
     Capita
    0.43
     Exempl
    0.42
    Activations Density 0.000%

    No Known Activations