© 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. 58535
    Prev
    Next
    INDEX
    Explanations

    `serialVersionUID` or `version`

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

    The neuron activates on numeric literal tokens (numbers) in code.

    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
    idées
    -0.99
     hjæl
    -0.93
    вають
    -0.92
    avaş
    -0.90
     ideen
    -0.90
     arbej
    -0.87
     circunstan
    -0.87
    ⅈ
    -0.86
    ::{
    -0.86
     henvis
    -0.85
    POSITIVE LOGITS
     one
    0.78
     serial
    0.75
    Departments
    0.75
    报道
    0.73
    üf
    0.73
     went
    0.72
     приходится
    0.72
    ്
    0.71
     Giud
    0.71
     so
    0.70
    Activations Density 0.001%

    No Known Activations