© 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. 235567
    Prev
    Next
    INDEX
    Explanations

    combinatorial or sequential information

    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
     was
    0.55
     would
    0.54
    。
    0.52
    ja
    0.51
     same
    0.50
     cannot
    0.50
    db
    0.49
    <0x80>
    0.49
     be
    0.49
    0
    0.49
    POSITIVE LOGITS
     بیاکتنې
    0.55
     ആക്രമ
    0.54
    ของการ
    0.53
     살펴보도록
    0.52
     கூறுக
    0.51
    onomic
    0.49
    bildungs
    0.49
     sporad
    0.49
    slaught
    0.49
    สำหรับ
    0.48
    Activations Density 0.000%

    No Known Activations