© 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. 34-GEMMASCOPE-RES-131K
    7. 63925
    Prev
    Next
    INDEX
    Explanations

    code, programming, and special characters

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

    This neuron is triggered by programming‐language tokens—identifiers, keywords, operators, and other code symbols.

    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
     SAMUEL
    -0.84
    ított
    -0.82
     acontece
    -0.80
    Caratteristiche
    -0.79
    positivos
    -0.78
     JORDAN
    -0.77
     chou
    -0.76
    تری
    -0.76
    toCharArray
    -0.76
    ıyı
    -0.75
    POSITIVE LOGITS
     eighteenth
    0.88
    beginning
    0.84
     address
    0.82
    *}{
    0.80
    ativen
    0.80
    conto
    0.77
    ilistic
    0.77
    ngoing
    0.77
     asterisk
    0.76
     стоимо
    0.76
    Activations Density 0.002%

    No Known Activations