© 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. 15547
    Prev
    Next
    INDEX
    Explanations

    formats for text and code

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

    The neuron detects numeric quantities expressed as decimal 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
     rusting
    0.89
     enraged
    0.84
     impregnated
    0.80
     evaporator
    0.79
     ums
    0.79
     ohms
    0.78
     maroon
    0.78
    홧
    0.78
     botão
    0.77
    kumar
    0.77
    POSITIVE LOGITS
     Що
    0.73
    ґ
    0.71
    OPEN
    0.71
    bbero
    0.71
     т
    0.70
     souligne
    0.69
    Of
    0.68
    нача
    0.68
     що
    0.67
     може
    0.67
    Activations Density 0.000%

    No Known Activations