© 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. 9441
    Prev
    Next
    INDEX
    Explanations

    scores, UI, my

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

    The neuron is triggered by sequences of digits (often with punctuation like hyphens), for example phone numbers or other multi‐digit numeric codes.

    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
     posteriores
    0.62
     baos
    0.61
     embeddings
    0.59
    🎟
    0.59
    ग्रियों
    0.56
     takže
    0.54
     entradas
    0.53
    했고
    0.53
     mexicanos
    0.53
     behandeling
    0.52
    POSITIVE LOGITS
     किंवा
    0.54
     或
    0.49
    NavigationBar
    0.49
    還是
    0.48
    或
    0.48
    或是
    0.47
     ឬ
    0.47
     Sunset
    0.47
     ሁሉ
    0.47
     või
    0.46
    Activations Density 1.305%

    No Known Activations