© 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. 2496
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens representing precise decimal measurements.

    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
     Nicholas
    0.70
     rara
    0.70
    IMENT
    0.68
     মজুমদার
    0.68
     Jimmy
    0.67
    谆
    0.66
    なければ
    0.66
     WHE
    0.66
    imentary
    0.65
     sincer
    0.65
    POSITIVE LOGITS
    Autres
    0.77
     kaart
    0.74
     Сою
    0.73
    ంగ్‌
    0.73
    dracht
    0.73
    掫
    0.73
     ด้าน
    0.71
    เรา
    0.71
     plages
    0.71
    อ
    0.71
    Activations Density 0.000%

    No Known Activations