© 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. 10273
    Prev
    Next
    INDEX
    Explanations

    sets and reps

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

    This neuron spotlights numeric score patterns (especially paired numbers with hyphens) as seen in match or set scores.

    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
    गेड
    0.57
    GK
    0.57
     bullpen
    0.56
    ੁੰ
    0.56
    ﻦ
    0.55
     baseman
    0.55
     elite
    0.53
    ÷
    0.52
    اتي
    0.51
     ungroup
    0.51
    POSITIVE LOGITS
     pengambilan
    0.58
     matchs
    0.57
    半島
    0.57
    Fast
    0.55
    を取
    0.55
    மொழி
    0.52
     prendere
    0.52
     schneller
    0.52
     Fast
    0.51
     அக
    0.50
    Activations Density 0.061%

    No Known Activations