© 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. 24-GEMMASCOPE-2-RES-16K
    7. 1932
    Prev
    Next
    INDEX
    Explanations

    championships league titles games

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

    This neuron detects numeric tokens, especially statistical or measurement values.

    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_24_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
    РА
    0.71
    Е
    0.70
    Ф
    0.66
    Та
    0.66
    ismillahirrah
    0.66
    До
    0.65
    Ва
    0.65
    襖
    0.65
    Вот
    0.64
    Об
    0.64
    POSITIVE LOGITS
     Pittsburgh
    0.81
     undefeated
    0.77
     reigning
    0.77
     defending
    0.76
     Wildcats
    0.74
     unbeaten
    0.73
     Falcons
    0.73
     Bulldogs
    0.71
     Chicago
    0.70
     Decatur
    0.70
    Activations Density 0.018%

    No Known Activations