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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128695
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on code function or method definitions (i.e., the signature tokens around a function declaration).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming language keywords and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     \
    -0.95
     Leben
    -0.91
    neous
    -0.89
    Life
    -0.87
    lahoma
    -0.86
     bł
    -0.86
    -]
    -0.85
    LOOP
    -0.85
    sizeCache
    -0.85
    Dopo
    -0.84
    POSITIVE LOGITS
     veta
    0.98
     vänt
    0.95
     pantalon
    0.91
     classico
    0.90
     pemas
    0.90
     from
    0.89
     taip
    0.89
     layanan
    0.88
     blivit
    0.86
     Depor
    0.85
    Activations Density 0.065%

    No Known Activations