© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6599
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (digits, measurements, decimal values), i.e. it detects numbers in the text.

    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_24_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
     CtApp
    0.63
     ไฟล์
    0.63
     xray
    0.61
     glTex
    0.60
    ඕ
    0.57
     ordinateur
    0.57
     sofas
    0.57
     dichas
    0.57
     The
    0.56
     কার্যত
    0.56
    POSITIVE LOGITS
    ,
    1.09
    .
    0.74
    ，
    0.71
    amey
    0.67
    ®,
    0.64
    ature
    0.62
    ukk
    0.61
    -
    0.59
    :
    0.59
    ems
    0.59
    Activations Density 0.512%

    No Known Activations