© 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. 247128
    Prev
    Next
    INDEX
    Explanations

    events, awards, champion, company

    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
    لی
    0.60
    میم
    0.55
    ה
    0.54
    Les
    0.53
    بی
    0.53
    MET
    0.52
    M
    0.52
    Ni
    0.51
    LIST
    0.50
     dobre
    0.49
    POSITIVE LOGITS
     అంతే
    0.46
    ığında
    0.46
    라인
    0.46
     सर्व
    0.45
     बालक
    0.45
     बगैर
    0.45
     रोमांच
    0.44
     прош
    0.44
    ısına
    0.44
     फौज
    0.44
    Activations Density 0.000%

    No Known Activations