© 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. 10-GEMMASCOPE-RES-131K
    4. 69173
    Prev
    Next
    INDEX
    Explanations

    programming keywords and methods

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

    The neuron fires on programming method or function call tokens (e.g., bind, exec, generate, select, mount, model, map, where).

    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
     that
    -1.92
     autunno
    -1.63
     marito
    -1.63
     orologio
    -1.57
     anticipo
    -1.49
     attacco
    -1.48
     perfetta
    -1.48
     adesi
    -1.43
     gemeinsamen
    -1.42
     navigazione
    -1.41
    POSITIVE LOGITS
    -
    1.66
    ou
    1.38
    o
    1.37
    Kemudian
    1.34
    <th>
    1.30
    没问题
    1.29
     $
    1.25
     «
    1.25
     ३
    1.24
    </strong>
    1.23
    Activations Density 0.020%

    No Known Activations