© 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. 77726
    Prev
    Next
    INDEX
    Explanations

    method event signatures

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

    The neuron is picking up on code‐specific syntax tokens (especially underscores in identifiers, parentheses, braces, and other C# code elements).

    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
    Boli
    -0.89
    crizione
    -0.83
     inters
    -0.81
    Alcal
    -0.81
    Interpret
    -0.80
    kezi
    -0.80
     patru
    -0.79
    慙
    -0.78
     parabola
    -0.78
     homeostasis
    -0.77
    POSITIVE LOGITS
     lưới
    0.96
     itens
    0.83
    Navigator
    0.82
     knapp
    0.81
    締切
    0.79
    MÁS
    0.77
     상세
    0.76
     gyer
    0.76
    ながらも
    0.75
     vínculos
    0.75
    Activations Density 0.003%

    No Known Activations