© 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. 89927
    Prev
    Next
    INDEX
    Explanations

    minOccurs, maxOccurs, and identifiers

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

    This neuron detects code‐specific tokens—identifiers, keywords, and other programming names (e.g. CamelCase or underscores) in source‐code blocks.

    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
     Versus
    -0.73
     Fisch
    -0.71
     Bytes
    -0.71
     Otto
    -0.69
     Cena
    -0.67
     chữ
    -0.67
     Stan
    -0.65
    丹
    -0.65
    expenses
    -0.65
    Stan
    -0.64
    POSITIVE LOGITS
    FormComponent
    0.73
     votación
    0.68
     prevention
    0.67
    Heights
    0.66
    丟
    0.66
    aii
    0.66
    Butt
    0.65
    Joachim
    0.65
    aie
    0.65
    balloon
    0.64
    Activations Density 0.042%

    No Known Activations