© 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. 12987
    Prev
    Next
    INDEX
    Explanations

    its role

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

    The neuron primarily activates on numeric tokens formatted as large decimal numbers (i.e. float‐style numerals).

    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
    ри
    0.99
    ᆼ
    0.89
    িজে
    0.79
    رد
    0.77
    рис
    0.72
    рек
    0.71
    ᇂ
    0.71
    ро
    0.70
    дача
    0.70
    ឹ
    0.70
    POSITIVE LOGITS
     tội
    0.78
     Seigneur
    0.77
    ua
    0.75
    avar
    0.75
    mt
    0.75
     mógł
    0.75
    牺牲
    0.74
    etti
    0.74
    te
    0.72
    amily
    0.72
    Activations Density 0.000%

    No Known Activations