© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89935
    Prev
    Next
    INDEX
    Explanations

    graphics, colors, or code structure

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

    This neuron activates on numeric literals (numbers) in the document.

    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
    <%=
    -0.86
    pylab
    -0.84
    antd
    -0.79
    🌁
    -0.76
     Ə
    -0.76
    manned
    -0.75
     DevComponents
    -0.75
     onResume
    -0.75
     Groves
    -0.74
    ⇡
    -0.74
    POSITIVE LOGITS
    elsey
    0.81
     jednej
    0.81
    viation
    0.80
     seleccionados
    0.77
     الأمريكي
    0.76
     following
    0.75
    PyExc
    0.74
    ilte
    0.73
     pocit
    0.73
     quatre
    0.73
    Activations Density 0.000%

    No Known Activations