© 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. 2948
    Prev
    Next
    INDEX
    Explanations

    accepting network connections

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

    This neuron fires on the punctuation of function‐call syntax—specifically the open‐ and close‐parentheses tokens around arguments.

    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
    toppers
    -0.87
     Objekte
    -0.86
     proteins
    -0.84
     sendMessage
    -0.77
    osamente
    -0.76
    ([])
    -0.74
    ิลปะ
    -0.73
    postal
    -0.73
     species
    -0.72
     lips
    -0.71
    POSITIVE LOGITS
     clients
    2.30
     client
    2.06
    clients
    1.85
     Clients
    1.83
     connections
    1.83
    Clients
    1.75
     connection
    1.73
     accepted
    1.61
    client
    1.52
     accept
    1.45
    Activations Density 0.046%

    No Known Activations