© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5295
    Prev
    Next
    INDEX
    Explanations

    baseball, MLB, pitcher, cap

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

    The neuron is primarily detecting numeric tokens—digits, numbers, and quantitative values 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_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
     Ekiti
    0.64
     Rashford
    0.62
     уче
    0.61
     косми
    0.61
    🐺
    0.61
     keluar
    0.60
    neural
    0.60
     πολι
    0.59
     Judo
    0.58
    ู่
    0.57
    POSITIVE LOGITS
     baseball
    2.17
     Baseball
    2.16
    Baseball
    2.06
    baseball
    1.92
     MLB
    1.84
    ⚾
    1.73
    MLB
    1.59
    野球
    1.52
     outfielder
    1.48
     pitcher
    1.44
    Activations Density 0.302%

    No Known Activations