© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6846
    Prev
    Next
    INDEX
    Explanations

    ability, choice, or possibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    ilty
    2.11
    usch
    2.10
    ijek
    2.05
    itech
    2.03
     movers
    1.96
    onk
    1.95
    مم
    1.94
    s
    1.93
    尻
    1.91
    surge
    1.89
    POSITIVE LOGITS
     TRY
    0.95
     überprüfen
    0.80
    THAN
    0.76
     listen
    0.75
    atever
    0.75
    HttpRequest
    0.72
    eliers
    0.71
     deprive
    0.69
    StdHandle
    0.69
     статья
    0.69
    Activations Density 0.154%

    No Known Activations