© 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. 13964
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

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

    The neuron activates on numeric tokens—quantities, measurements, counts, or other numbers 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
    0
    -2.98
    1
    -2.95
    2
    -2.66
    i
    -2.28
    <
    -2.22
    7
    -2.16
    3
    -2.14
     -
    -2.13
    經典
    -2.11
    也會
    -2.02
    POSITIVE LOGITS
    𐐀
    2.30
    ㇼ
    2.25
    毉
    2.14
    inição
    2.14
    ☏
    2.08
    ?
    2.03
     myriad
    2.03
    噤
    2.02
    豢
    2.00
    
    2.00
    Activations Density 0.001%

    No Known Activations