© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38238
    Prev
    Next
    INDEX
    Explanations

    mathematical and code structures

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

    The neuron strongly activates on code‐ or math‐style punctuation and operator symbols (e.g. asterisks, parentheses, “*”, “(”, “)*”, etc.).

    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
    photographe
    -0.81
     információk
    -0.78
     Functional
    -0.76
     dibanding
    -0.75
     молоко
    -0.75
     cintur
    -0.73
     lisäksi
    -0.73
     beserta
    -0.72
    ческий
    -0.72
    интере
    -0.72
    POSITIVE LOGITS
     contratto
    0.90
     realizzare
    0.87
    graphique
    0.84
    AMAZ
    0.83
     pairwise
    0.83
     Mask
    0.83
     aero
    0.82
     следует
    0.81
     colline
    0.81
     avendo
    0.80
    Activations Density 0.000%

    No Known Activations