© 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. 152959
    Prev
    Next
    INDEX
    Explanations

    engineer design

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

    unexpected response, file, pattern

    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
    ing
    0.54
    Changed
    0.48
    <unused1646>
    0.46
    ARY
    0.45
    kata
    0.45
    ythe
    0.44
    grocery
    0.44
    akati
    0.44
     หา
    0.43
     souhaitez
    0.43
    POSITIVE LOGITS
    髻
    0.44
    轎
    0.44
    記錄
    0.43
     offenses
    0.43
    他们的
    0.43
     reali
    0.42
     착
    0.42
     Adirond
    0.41
    门口
    0.41
    健
    0.41
    Activations Density 0.001%

    No Known Activations