© 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. 62413
    Prev
    Next
    INDEX
    Explanations

    configuration files or code

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

    The neuron strongly activates on code‐related declaration and metadata tokens (e.g. import statements, function or class identifiers, compiler directives, JSON keys, copyright notices, etc.).

    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
    Fernseh
    -0.73
    DESCRIP
    -0.68
    预期
    -0.68
    jian
    -0.67
     Constru
    -0.67
     Affiliations
    -0.66
     Nao
    -0.66
     DESCRIPT
    -0.65
     fuchsia
    -0.65
    relief
    -0.65
    POSITIVE LOGITS
    versaire
    0.70
    GE
    0.64
     Relative
    0.63
    ابت
    0.63
     painting
    0.63
     LLC
    0.62
    Relative
    0.61
     arbete
    0.60
     relative
    0.60
     stra
    0.59
    Activations Density 0.082%

    No Known Activations