© 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. 92296
    Prev
    Next
    INDEX
    Explanations

    conference titles and comparisons

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

    science and practical applications

    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
     appareil
    0.50
    途径
    0.44
    류
    0.44
     internationaux
    0.44
     ennemis
    0.43
    ？
    0.43
    ेंगू
    0.43
    റില്‍
    0.43
    也好
    0.42
     aident
    0.42
    POSITIVE LOGITS
     Crowe
    0.53
     Biotechn
    0.48
     Gus
    0.48
    PE
    0.46
    scientist
    0.46
     Typh
    0.45
     gü
    0.45
     એમ
    0.44
     geologist
    0.44
    +)
    0.44
    Activations Density 0.001%

    No Known Activations