© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5256
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on floating‐point numeric tokens (numbers with decimal components).

    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
     شدم
    0.79
     respectivos
    0.77
    ప్రదేశ్
    0.73
    સ
    0.73
    ()}")
    0.72
     Considerations
    0.71
     посмотреть
    0.70
     попробовать
    0.70
     respectivas
    0.69
     შეგიძლიათ
    0.68
    POSITIVE LOGITS
    ing
    0.99
    ar
    0.90
    im
    0.84
    ’
    0.82
    an
    0.79
    liga
    0.79
    ahuje
    0.79
    n
    0.77
    am
    0.75
    nian
    0.75
    Activations Density 0.000%

    No Known Activations