© 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. 10-GEMMASCOPE-RES-131K
    7. 9911
    Prev
    Next
    INDEX
    Explanations

    UPC, GTP, VDC, PTC

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

    This neuron activates on numeric tokens (digits and numbers, including codes, measurements, and decimal values).

    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
     '
    -3.80
    ’
    -3.06
    }
    -2.92
    犼
    -2.83
    ที่
    -2.66
    -'
    -2.58
    鴬
    -2.58
    躂
    -2.55
    !"
    -2.50
    珰
    -2.38
    POSITIVE LOGITS
    ｱ
    2.77
    几位
    2.70
    If
    2.67
    Perhaps
    2.61
    It
    2.55
    ｷ
    2.45
    Some
    2.42
    嵛
    2.41
    
    2.38
    鯓
    2.38
    Activations Density 0.015%

    No Known Activations