© 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. 3639
    Prev
    Next
    INDEX
    Explanations

    file headers and version info

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

    This neuron identifies long runs or clusters of ASCII-art characters (e.g., repeated underscores, pipes, asterisks, slashes) used to draw diagrams or decorative borders.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     should
    -1.06
     which
    -1.05
     while
    -1.01
     their
    -0.97
     when
    -0.97
     since
    -0.97
     betting
    -0.96
     Since
    -0.96
     well
    -0.95
     Despite
    -0.94
    POSITIVE LOGITS
     Fores
    0.90
    changing
    0.90
    ignons
    0.89
    ੮
    0.89
     interwoven
    0.88
    也不
    0.86
    柔ら
    0.85
    Abort
    0.85
    covering
    0.84
    GAIN
    0.84
    Activations Density 0.008%

    No Known Activations