© 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. 22-GEMMASCOPE-RES-131K
    7. 38939
    Prev
    Next
    INDEX
    Explanations

    numerical data and quantities

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

    The neuron is specialized for spotting numeric tokens (numbers, digits, and numeric punctuation) 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_22/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
    $_['
    -1.08
     intptr
    -1.03
     svå
    -1.02
     Porque
    -1.02
    ]=>
    -1.00
    האם
    -1.00
     musée
    -0.99
    ırken
    -0.98
     mxArray
    -0.98
     cherche
    -0.97
    POSITIVE LOGITS
     and
    1.21
    eynman
    1.06
     instead
    1.05
     entwickeln
    0.98
     NONE
    0.98
    ecirc
    0.96
     cubiertos
    0.96
     postulated
    0.95
     myriad
    0.95
    还是要
    0.95
    Activations Density 0.038%

    No Known Activations