© 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. 9493
    Prev
    Next
    INDEX
    Explanations

    describing traits or providers

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

    The neuron selectively responds to numeric measurement values—especially floating-point numbers appearing in the text.

    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
    igueur
    0.86
     convoc
    0.81
    وفيق
    0.81
    agian
    0.80
    灯
    0.79
     précie
    0.79
    abases
    0.77
     rése
    0.77
    énieur
    0.77
    ónio
    0.77
    POSITIVE LOGITS
    de
    0.93
     варианты
    0.74
    ;
    0.73
    a
    0.73
    는
    0.71
    бере
    0.68
    head
    0.68
    TimeTo
    0.68
     frá
    0.68
    ం
    0.68
    Activations Density 0.000%

    No Known Activations