© 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. 10-GEMMASCOPE-RES-131K
    7. 40760
    Prev
    Next
    INDEX
    Explanations

    with numbers

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

    The neuron activates on numeric tokens (numbers and numeric strings) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     there
    -1.70
    𓆜
    -1.70
     cauza
    -1.64
     samego
    -1.61
     should
    -1.59
     convenio
    -1.54
     are
    -1.53
     studia
    -1.52
     ใหม่
    -1.52
    
    -1.49
    POSITIVE LOGITS
    stood
    2.50
     regard
    2.47
    ing
    2.42
    standing
    2.16
    </strong>
    2.09
    ering
    1.98
     (
    1.98
    a
    1.93
     regards
    1.84
    holds
    1.71
    Activations Density 0.044%

    No Known Activations