© 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. 129635
    Prev
    Next
    INDEX
    Explanations

    Fourteenth Court

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

    The neuron activates on numeric tokens—especially numbers with digits and decimal points.

    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
    
    -2.31
    atiques
    -2.14
     fieles
    -2.11
    They
    -2.05
    Those
    -2.00
    𐐪
    -1.98
    Its
    -1.96
    τού
    -1.96
    渃
    -1.95
     вместе
    -1.92
    POSITIVE LOGITS
    \
    3.09
    '
    2.64
    .
    2.64
    我先
    2.00
    selbe
    1.95
    1
    1.95
    ar
    1.91
    明白了
    1.89
    籥
    1.68
     WHICH
    1.63
    Activations Density 0.042%

    No Known Activations