© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111443
    Prev
    Next
    INDEX
    Explanations

    code closing characters

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

    closing syntax for code statements, particularly closing parentheses and braces.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron activates on numeric literals (numbers) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    :
    -1.82
     this
    -1.64
     venezol
    -1.55
    \
    -1.52
    /
    -1.50
     таком
    -1.47
    casila
    -1.46
     такое
    -1.45
     этой
    -1.45
     reciente
    -1.45
    POSITIVE LOGITS
    k
    1.94
     was
    1.59
     and
    1.49
    ');
    1.45
    ścioła
    1.38
    :✨
    1.34
    ✨:
    1.32
    Whisper
    1.32
     vedere
    1.31
    gehende
    1.30
    Activations Density 0.020%

    No Known Activations