© 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. 10364
    Prev
    Next
    INDEX
    Explanations

    Français, Spanish, German, English UI elements

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

    This neuron activates on tokens occurring in numeric contexts—i.e. words immediately following numbers or percentages.

    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
    ung
    0.65
    “
    0.64
    fli
    0.64
    occup
    0.63
     plasmids
    0.63
    investment
    0.62
     শ
    0.61
     অনুষ্ঠানে
    0.61
    fram
    0.61
    <0x0D>
    0.61
    POSITIVE LOGITS
     cuarta
    0.94
     cuarto
    0.91
     avión
    0.89
     Français
    0.82
    াতাড়ি
    0.81
     deportes
    0.81
    केशन
    0.80
     muchachos
    0.80
     Tope
    0.79
    ngày
    0.79
    Activations Density 0.000%

    No Known Activations