© 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. 34-GEMMASCOPE-RES-131K
    7. 58231
    Prev
    Next
    INDEX
    Explanations

    code parameters and events

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

    This neuron detects programming‐style tokens—symbols and syntax elements typical of code (e.g. $, ->, function names, numeric IDs).

    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
     busiest
    -0.80
    χαν
    -0.78
    έν
    -0.77
    Elabor
    -0.76
     nâu
    -0.74
    emer
    -0.74
    Deutsch
    -0.71
     wzgl
    -0.71
    nail
    -0.71
    isons
    -0.69
    POSITIVE LOGITS
     event
    1.27
     incoming
    1.05
     args
    1.05
     msg
    0.99
     request
    0.95
     triggering
    0.90
    args
    0.90
     calldata
    0.90
    EventArgs
    0.90
     caller
    0.89
    Activations Density 0.067%

    No Known Activations