© 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. 3995
    Prev
    Next
    INDEX
    Explanations

    prenatal care

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

    The neuron selectively activates on numeric tokens (decimal numbers) in the text.

    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
     oczywiście
    0.90
    사에
    0.80
    tia
    0.77
    이라
    0.77
     лишь
    0.77
    라
    0.77
     nikdy
    0.76
     пузы
    0.75
    nú
    0.74
     adição
    0.74
    POSITIVE LOGITS
    къ
    0.79
    preg
    0.76
     conce
    0.74
    conce
    0.73
    п
    0.73
    सीबी
    0.71
    ґ
    0.70
    pregnancy
    0.70
    мети
    0.70
     trac
    0.70
    Activations Density 0.000%

    No Known Activations