© 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. 108109
    Prev
    Next
    INDEX
    Explanations

    before starting, before shipment, before you

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

    punctuation and word boundaries

    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
     mę
    0.54
     žene
    0.50
     sogar
    0.46
     možno
    0.46
     একইভাবে
    0.46
     unidades
    0.46
     Aufmerksamkeit
    0.46
     möglichen
    0.45
     ông
    0.45
     ////
    0.45
    POSITIVE LOGITS
    ophil
    0.52
    힣
    0.46
    geolocation
    0.45
    ta
    0.45
    syair
    0.45
    hend
    0.45
     coalition
    0.45
    <0xBA>
    0.44
    そうです
    0.43
     mitigated
    0.43
    Activations Density 0.002%

    No Known Activations