© 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. 211660
    Prev
    Next
    INDEX
    Explanations

    training and solutions

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

    generating concepts and dynamics

    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
    本文
    0.50
    廬
    0.46
    自然的
    0.45
    茎
    0.45
     त
    0.44
    ཨ
    0.44
     канди
    0.43
    رف
    0.42
    副
    0.42
     द
    0.42
    POSITIVE LOGITS
     geração
    0.52
     ekip
    0.48
     gunshot
    0.47
     brigade
    0.47
    보험
    0.46
     Solskjaer
    0.46
     etapas
    0.46
    Generation
    0.45
     explosives
    0.45
     ။
    0.45
    Activations Density 0.002%

    No Known Activations