© 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. 129624
    Prev
    Next
    INDEX
    Explanations

    collocation patterns

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

    common phrases and continuations

    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
     precipitate
    0.40
    PLUS
    0.39
    8
    0.39
    Transforms
    0.39
     PCM
    0.39
     refinance
    0.39
     Maison
    0.39
     double
    0.39
     refund
    0.38
     Palazzo
    0.38
    POSITIVE LOGITS
    àn
    0.52
    筧
    0.49
    ịa
    0.48
    ሑ
    0.47
    প্
    0.47
    emene
    0.46
    䏹
    0.46
     ketentuan
    0.46
     golongan
    0.46
    近年来
    0.46
    Activations Density 0.003%

    No Known Activations