© 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. 10-GEMMASCOPE-RES-131K
    7. 44437
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    This neuron fires on code punctuation marking the end of function or method calls—specifically sequences of closing parentheses/brackets (and quotes) plus a dot or semicolon, e.g. “]);”, “");”, “)).”

    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
    If
    -2.98
    You
    -2.97
    \
    -2.75
    6
    -2.55
     usai
    -2.53
    8
    -2.47
    4
    -2.39
    駛
    -2.38
     или
    -2.36
    ........
    -2.30
    POSITIVE LOGITS
    </h2>
    3.75
    僦
    2.52
    雠
    2.48
    
    2.47
     excellente
    2.47
    
    2.44
    獃
    2.42
     kaas
    2.39
     mág
    2.39
     jao
    2.38
    Activations Density 0.002%

    No Known Activations