© 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. 107867
    Prev
    Next
    INDEX
    Explanations

    file headers and code delimiters

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

    This neuron detects numeric tokens (numeric literals and numbers, including units and percentages) 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
    <!--[
    -0.92
    这不是
    -0.91
    밌
    -0.86
    alignItems
    -0.85
    ZA
    -0.79
    addPreferredGap
    -0.77
    initComponents
    -0.77
     diễn
    -0.75
     dashing
    -0.75
    jk
    -0.74
    POSITIVE LOGITS
     تھا
    0.81
     réunis
    0.81
    cartoon
    0.79
    universo
    0.77
     riva
    0.77
    pousada
    0.77
     répertoire
    0.76
    carboxylic
    0.76
    jTextField
    0.75
    Spinach
    0.75
    Activations Density 0.002%

    No Known Activations