© 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. 63419
    Prev
    Next
    INDEX
    Explanations

    type definitions or programming syntax

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

    The neuron fires on code‐style or technical tokens—especially numbers, symbols, and code keywords—i.e. segments that look like programming or spec text.

    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
    ρώ
    -0.74
    برگ
    -0.69
    Initializer
    -0.69
     kimdir
    -0.69
    ータル
    -0.68
    Rural
    -0.68
    ctives
    -0.68
    isRequired
    -0.68
    nte
    -0.67
     niem
    -0.67
    POSITIVE LOGITS
     puffer
    0.73
    tets
    0.66
    AddAttribute
    0.64
     heron
    0.64
     Bakker
    0.64
     Generators
    0.64
    鱇
    0.64
     sable
    0.63
     lhs
    0.63
     Hound
    0.63
    Activations Density 0.073%

    No Known Activations