© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10059
    Prev
    Next
    INDEX
    Explanations

    exercise classification

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

    The neuron signals the very first substantive word or content token at the start of each new paragraph or text block.

    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_31_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
    Ử
    0.57
     Becoming
    0.55
     Novi
    0.54
    ومي
    0.54
     Marcus
    0.54
     Physiological
    0.54
    HALF
    0.54
     Life
    0.53
     সিরাজ
    0.53
     Determining
    0.53
    POSITIVE LOGITS
     diss
    0.63
     खो
    0.58
    :%
    0.57
     horaires
    0.57
    thew
    0.55
     chronique
    0.55
    يئة
    0.55
     vendredi
    0.54
    顯
    0.54
     calendrier
    0.54
    Activations Density 0.000%

    No Known Activations