© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9157
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on tokens representing numbers or numeric values (e.g. floats, measurements, years).

    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
    grouped
    0.77
    up
    0.76
    perform
    0.76
    ออกมา
    0.75
    <strong>
    0.75
    cb
    0.74
    ਰ
    0.72
    help
    0.70
    remember
    0.70
    а
    0.68
    POSITIVE LOGITS
     alemán
    0.86
     vistas
    0.85
     Lang
    0.84
     atractivo
    0.84
     inglés
    0.82
     Ó
    0.80
     vê
    0.80
     correcto
    0.80
    ంట్
    0.80
     rectas
    0.80
    Activations Density 0.014%

    No Known Activations