© 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. 118850
    Prev
    Next
    INDEX
    Explanations

    code name and type references

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

    The neuron is firing on code‐style syntax—especially method/attribute calls (identifiers immediately followed by “(”) and the indentation/punctuation typical of code blocks.

    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
     jeste
    -0.84
    authors
    -0.82
     upgrades
    -0.82
     oble
    -0.82
     unwanted
    -0.80
     DELLE
    -0.80
    營業
    -0.80
     conteúdo
    -0.79
    态度
    -0.79
     warszawa
    -0.79
    POSITIVE LOGITS
    nameof
    3.28
     nameof
    3.14
     named
    0.97
     nombre
    0.87
     name
    0.87
     names
    0.86
     constante
    0.85
     แล้ว
    0.85
     typeof
    0.84
     باسم
    0.83
    Activations Density 0.015%

    No Known Activations