© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11262
    Prev
    Next
    INDEX
    Explanations

    The neuron chiefly detects numeric tokens (e.g. dates, counts, ratings, and other numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NOW
    0.54
    UDE
    0.52
    נט
    0.50
    IMA
    0.50
    NZ
    0.50
    ipas
    0.50
    1
    0.50
    *****",
    0.50
    stö
    0.49
    neither
    0.49
    POSITIVE LOGITS
    configured
    0.73
     configured
    0.72
     recorded
    0.70
     applicable
    0.70
     entspre
    0.67
     definido
    0.66
     formatted
    0.66
    specified
    0.65
     شناخته
    0.65
    <0x85>
    0.64
    Activations Density 0.041%

    No Known Activations