© 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. 82878
    Prev
    Next
    INDEX
    Explanations

    refunds, orders, integration, alerting

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

    allows, options, buttons

    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
     lundi
    0.50
     vrijdag
    0.48
    iamo
    0.47
     τη
    0.45
     urldecode
    0.45
     nieder
    0.44
    産
    0.44
    홧
    0.44
    ೃಷ್ಣ
    0.44
     roundup
    0.44
    POSITIVE LOGITS
    allows
    0.49
     Options
    0.49
    deleteOne
    0.46
    options
    0.45
    focusable
    0.45
    panels
    0.45
    getTransforms
    0.44
     Allows
    0.43
     Panels
    0.43
    Allows
    0.43
    Activations Density 0.000%

    No Known Activations