© 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. 12049
    Prev
    Next
    INDEX
    Explanations

    The neuron specializes in spotting decimal numbers (numeric tokens containing a point).

    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
    Mega
    0.56
    mega
    0.55
    calculator
    0.54
    reply
    0.53
    five
    0.53
     Servers
    0.52
     calculators
    0.52
    ｜
    0.52
     servers
    0.52
    central
    0.51
    POSITIVE LOGITS
    ữu
    0.58
    ूला
    0.57
     Mercantile
    0.57
    Ꮏ
    0.57
    Ꮄ
    0.57
     dériv
    0.57
     transcendent
    0.57
    anone
    0.55
     amide
    0.55
     traitements
    0.55
    Activations Density 0.000%

    No Known Activations