© 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. 31-GEMMASCOPE-2-RES-16K
    7. 3037
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is detect numerical values and numeric tokens (e.g. digits, decimals, and numeric symbols).

    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
     "{{
    0.87
     \"
    0.69
    {{
    0.68
    ="{{
    0.62
     "
    0.61
     poit
    0.61
     “
    0.60
     pře
    0.58
    <0xE3>
    0.56
     ”
    0.55
    POSITIVE LOGITS
     [
    1.58
     [],
    1.27
     []
    1.24
     ['./
    1.22
     [,
    1.22
     [])
    1.20
     [$
    1.20
     [_
    1.20
     [-
    1.19
     [<
    1.15
    Activations Density 0.024%

    No Known Activations