© 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. 11765
    Prev
    Next
    INDEX
    Explanations

    dice rolls

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

    The neuron selectively activates on numeric tokens—especially decimal or floating‐point values—within the technical 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_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
     २४
    0.64
     چهار
    0.64
     ④
    0.63
    四
    0.61
     FOUR
    0.60
     ۱۴
    0.59
     四
    0.57
     ted
    0.56
     quarta
    0.55
     Quartet
    0.55
    POSITIVE LOGITS
     fifth
    1.24
    ⑤
    1.16
    fifth
    1.15
     quinto
    1.11
     Fifth
    1.09
    Fifth
    1.09
    第五
    1.03
     пя
    1.01
     cinquième
    1.01
    पांच
    1.01
    Activations Density 0.149%

    No Known Activations