© 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. 92245
    Prev
    Next
    INDEX
    Explanations

    finalist campaign

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

    testing code for correctness

    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
     wond
    0.46
     opdracht
    0.45
     lega
    0.44
     आढ
    0.44
    sne
    0.43
     bút
    0.43
     tornare
    0.43
    s
    0.43
    serr
    0.42
     kredi
    0.42
    POSITIVE LOGITS
    נה
    0.51
     Myles
    0.47
    armed
    0.46
     armed
    0.46
    нес
    0.45
     سپورت
    0.45
     deportivas
    0.45
     ইলেক্ট
    0.43
    ؤول
    0.43
    নমেন্ট
    0.43
    Activations Density 0.000%

    No Known Activations