© 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. 9879
    Prev
    Next
    INDEX
    Explanations

    produces Trio, Respect, rules, shopping

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

    The neuron activates on numeric tokens containing decimal points (floating-point numbers).

    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
     ASS
    0.77
    ೋ
    0.73
     ---
    0.69
     луч
    0.68
     ―
    0.68
     وزير
    0.66
    Lieutenant
    0.66
     тыся
    0.65
    Sage
    0.64
    vette
    0.64
    POSITIVE LOGITS
    罍
    0.89
    鹬
    0.86
    رحب
    0.80
     אבל
    0.79
    ছনে
    0.78
     mengungkapkan
    0.78
    open
    0.78
    ামূলক
    0.78
     estimés
    0.78
    没人
    0.77
    Activations Density 0.000%

    No Known Activations