© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12259
    Prev
    Next
    INDEX
    Explanations

    const, C++ code, questions

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

    The neuron fires on occurrences of “()” parentheses in code, i.e. empty‐argument lists in function definitions or calls.

    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
    όμε
    -0.77
     даже
    -0.76
    xfc
    -0.75
    adog
    -0.75
    profile
    -0.75
    Če
    -0.75
    läge
    -0.75
     ARISING
    -0.75
     viva
    -0.73
     onCancelled
    -0.73
    POSITIVE LOGITS
     const
    2.33
     than
    2.17
    const
    1.98
     then
    1.15
     constriction
    1.07
     as
    0.96
     constable
    0.95
    '!
    0.90
     constancy
    0.89
     anstatt
    0.86
    Activations Density 0.003%

    No Known Activations