© 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. 153267
    Prev
    Next
    INDEX
    Explanations

    study, supplement, collateral, exclusives

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

    numeric conversion or specific 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
     ഒന്നും
    0.50
     เตรียม
    0.47
    Fen
    0.46
     যের
    0.46
    ма
    0.46
     ഒന്ന
    0.45
    ا
    0.45
    Hb
    0.44
     Tatha
    0.44
     definitiv
    0.44
    POSITIVE LOGITS
     commandant
    0.52
    volved
    0.47
    iculas
    0.44
    ricamente
    0.44
    िकांत
    0.43
    स्तिक
    0.43
    ract
    0.42
    这些人
    0.42
    यर
    0.42
    वीय
    0.42
    Activations Density 0.000%

    No Known Activations