© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3602
    Prev
    Next
    INDEX
    Explanations

    hyphens and dashes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     russischen
    -0.78
     بیمارستان
    -0.73
    /+
    -0.71
    鐺
    -0.70
    HRS
    -0.70
    緻
    -0.70
     parlak
    -0.69
    culature
    -0.69
    詫
    -0.69
    くな
    -0.68
    POSITIVE LOGITS
     hyphen
    3.38
     dash
    2.64
    hyphen
    2.61
     dashes
    2.45
    Dash
    2.31
    dash
    2.30
     Dash
    2.28
    Hy
    2.03
     DASH
    2.03
     "-"
    1.98
    Activations Density 0.070%

    No Known Activations