© 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. 14954
    Prev
    Next
    INDEX
    Explanations

    numbers after comma

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

    The neuron strongly activates on numeric tokens (multi‐digit 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_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
     peluche
    -1.95
     linge
    -1.93
     biela
    -1.88
     laine
    -1.78
     vernis
    -1.77
     cuir
    -1.75
     esponja
    -1.70
     dager
    -1.67
     bré
    -1.65
     banane
    -1.64
    POSITIVE LOGITS
    ,
    2.11
    J
    1.94
    L
    1.84
    V
    1.82
    S
    1.80
    l
    1.80
    C
    1.77
    M
    1.77
    B
    1.75
    F
    1.73
    Activations Density 0.014%

    No Known Activations