© 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. 2480
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that occur in passages giving precise numeric details—e.g. times, hours, or other factual figures.

    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
    d
    0.93
    m
    0.91
    b
    0.88
    c
    0.86
    us
    0.86
    er
    0.82
    n
    0.82
    é
    0.82
    u
    0.81
    r
    0.81
    POSITIVE LOGITS
     llamó
    0.93
     botão
    0.89
     долла
    0.89
     endereço
    0.88
     автомобилей
    0.86
     dermatitis
    0.86
     desgaste
    0.85
     diseños
    0.84
     montaña
    0.84
     desenhos
    0.84
    Activations Density 0.000%

    No Known Activations