© 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. 85272
    Prev
    Next
    INDEX
    Explanations

    common phrase starters

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

    lists and punctuation

    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
    ล
    0.43
    REIB
    0.42
     erklärte
    0.41
    實際上
    0.41
    GN
    0.40
     alatt
    0.40
    ποι
    0.40
    λ
    0.39
     milit
    0.38
    ̉
    0.38
    POSITIVE LOGITS
     Oka
    0.53
    ógicos
    0.48
     seepage
    0.48
     उत्कृष्टता
    0.47
     円
    0.46
     normalization
    0.46
     locomotion
    0.46
     いっ
    0.46
    もしくは
    0.45
     ഉൾ
    0.45
    Activations Density 0.000%

    No Known Activations