© 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. 152673
    Prev
    Next
    INDEX
    Explanations

    days, bills, and services

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

    bullet points*and.**

    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
    Not in Any Lists

    No Comments

    Negative Logits
     등장
    0.52
     hatırl
    0.49
     réussi
    0.47
    turkish
    0.46
    🏦
    0.46
     refleks
    0.46
    ebabkan
    0.46
     způ
    0.46
     setengah
    0.46
     naturels
    0.45
    POSITIVE LOGITS
    B
    0.58
    z
    0.55
    By
    0.54
    o
    0.53
    Blob
    0.53
    b
    0.52
    an
    0.52
    Route
    0.50
    Gun
    0.50
    Dip
    0.50
    Activations Density 0.000%

    No Known Activations