© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7099
    Prev
    Next
    INDEX
    Explanations

    software documentation and code versioning

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

    The neuron activates on snippets of source code and programming‐related tokens (e.g. variable names, function calls, punctuation), i.e. it detects code fragments.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     definitivamente
    -0.75
     fruitless
    -0.74
    kies
    -0.73
     muta
    -0.71
     Mitar
    -0.70
     Nodes
    -0.70
     Maske
    -0.69
    зов
    -0.68
     metast
    -0.68
     nourished
    -0.67
    POSITIVE LOGITS
    이다
    0.82
    ვი
    0.76
     element
    0.75
     Kobe
    0.75
     國
    0.74
    Ajax
    0.71
    descri
    0.69
    anty
    0.69
    asin
    0.68
    isible
    0.68
    Activations Density 0.015%

    No Known Activations