© 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. 1898
    Prev
    Next
    INDEX
    Explanations

    two followed by a noun

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

    The neuron activates on numeric tokens (quantities, measurements, counts, prices, etc.).

    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
    さまざ
    0.61
    데이터
    0.60
    .??.??"]
    0.59
    Ко
    0.59
    Inicio
    0.57
    Вы
    0.56
    Го
    0.56
    Ге
    0.55
    Жи
    0.55
    䚲
    0.55
    POSITIVE LOGITS
     tablespoons
    0.72
     thirds
    0.72
     dozen
    0.71
     puluh
    0.71
     sided
    0.71
     hundred
    0.70
     gatos
    0.70
     двух
    0.69
    つの
    0.69
    fifths
    0.68
    Activations Density 0.103%

    No Known Activations