© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27716
    Prev
    Next
    INDEX
    Explanations

    events and emissions

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

    The neuron is keyed to spotting numeric literal tokens (i.e. number constants) in the 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_22/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
     in
    -1.04
    寇
    -1.01
     herren
    -0.95
     freundlichen
    -0.93
     também
    -0.90
     then
    -0.90
    racuse
    -0.90
    ствий
    -0.89
    ambassade
    -0.88
     kuah
    -0.88
    POSITIVE LOGITS
     départ
    0.90
     утром
    0.89
     Emissions
    0.89
    柢
    0.86
     Ausgabe
    0.86
    \]
    0.83
     quienes
    0.82
    输出
    0.82
    drip
    0.82
     Emission
    0.82
    Activations Density 0.006%

    No Known Activations