© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25717
    Prev
    Next
    INDEX
    Explanations

    numerical expressions and quantities

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

    The neuron is detecting numeric digit characters (i.e. sequences of Arabic numerals).

    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
    ğiniz
    -0.84
    gheny
    -0.78
    CLP
    -0.77
     utmost
    -0.70
    habitation
    -0.69
    דות
    -0.69
    cccccccc
    -0.68
    tablissement
    -0.68
    開封
    -0.68
    vz
    -0.67
    POSITIVE LOGITS
    setti
    0.81
     CONCLUSION
    0.79
    THESIS
    0.77
     DETAILS
    0.75
    ฬ
    0.74
     gelatin
    0.71
    گرام
    0.68
    SITE
    0.68
    mors
    0.68
     durchschnitt
    0.67
    Activations Density 0.081%

    No Known Activations