© 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. 106362
    Prev
    Next
    INDEX
    Explanations

    copy at

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

    The neuron detects slash-delimited code paths (e.g. package import paths) in source files.

    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
    contributions
    -0.83
    fom
    -0.81
    Чыганаклар
    -0.80
     contributo
    -0.79
    واه
    -0.77
     miljoen
    -0.76
    fizz
    -0.75
    🇵
    -0.75
     februari
    -0.72
    WAV
    -0.72
    POSITIVE LOGITS
    DeepCopy
    1.02
    richTextPanel
    0.83
    ñana
    0.82
     Pflicht
    0.77
     никак
    0.77
     cipolla
    0.75
     intellig
    0.75
    ூ
    0.75
    peg
    0.75
     superficial
    0.75
    Activations Density 0.002%

    No Known Activations