© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102827
    Prev
    Next
    INDEX
    Explanations

    programming code and visual elements

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

    The neuron strongly activates on programming‐style tokens—identifiers, code keywords, punctuation, and CamelCase names—i.e. it detects code snippets.

    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
     jednoduch
    -0.82
    لاعات
    -0.79
    Jakub
    -0.75
     Raila
    -0.75
     UB
    -0.72
     Biotech
    -0.70
     hairline
    -0.69
    PIO
    -0.68
    mping
    -0.68
     Outer
    -0.68
    POSITIVE LOGITS
    animations
    0.96
    alpha
    0.83
     body
    0.82
    body
    0.81
    🦷
    0.80
     benda
    0.79
    ategorie
    0.79
     アニメ
    0.77
    anchor
    0.76
     '');
    0.75
    Activations Density 0.003%

    No Known Activations