© 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. 34-GEMMASCOPE-RES-131K
    7. 1042
    Prev
    Next
    INDEX
    Explanations

    arithmetic mean, award recipient, object size

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

    The neuron fires primarily on numeric tokens—especially code‐style indices, version numbers, and other multi‐digit numerals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ETO
    -0.72
    dą
    -0.71
     Argon
    -0.69
     registration
    -0.67
    checkable
    -0.66
    trà
    -0.66
    raum
    -0.64
    bda
    -0.64
    cía
    -0.63
    ohan
    -0.63
    POSITIVE LOGITS
     sosi
    0.77
     Bort
    0.71
     samoch
    0.71
    ž
    0.71
     connaissance
    0.70
     mínimo
    0.70
     pollin
    0.70
     Pseudo
    0.69
    Ст
    0.69
     cutlery
    0.68
    Activations Density 0.029%

    No Known Activations