© 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. 12236
    Prev
    Next
    INDEX
    Explanations

    function name or variable declaration

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

    The neuron fires on tokens that kick off code‐snippets or definitions—things like “function”, “const”, “var”, “export”, or comment delimiters—i.e. markers of new code statements or declarations.

    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
     loadImage
    -0.99
    getOwner
    -0.95
    etes
    -0.94
    jacks
    -0.90
    ELTS
    -0.90
    setattr
    -0.89
    şti
    -0.89
    naires
    -0.88
    getPhone
    -0.86
     owne
    -0.84
    POSITIVE LOGITS
     get
    3.69
    获取
    3.00
     obtain
    2.53
     getting
    2.48
    get
    2.41
     Get
    2.39
     获取
    2.36
     gets
    2.33
    得到
    2.17
     find
    2.14
    Activations Density 0.045%

    No Known Activations