© 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. 21262
    Prev
    Next
    INDEX
    Explanations

    special characters and code snippets

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

    The neuron strongly activates on numeric literals and related punctuation (digits, operators, and separators) in code or formula contexts.

    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
     eficientes
    -1.23
     remet
    -1.16
    ">
    -1.14
    辈子
    -1.14
     sure
    -1.13
    culas
    -1.13
    oursquare
    -1.12
    力の
    -1.11
    altitude
    -1.10
     zase
    -1.10
    POSITIVE LOGITS
     espri
    1.62
    ♪♪
    1.55
     /
    1.52
     $/$
    1.45
     now
    1.45
     /$
    1.44
    
    1.42
    2
    1.41
     notare
    1.40
     ducato
    1.37
    Activations Density 0.142%

    No Known Activations