© 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. 15004
    Prev
    Next
    INDEX
    Explanations

    internal, different, extracted control

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

    The neuron fires on the first substantive content word that starts a new paragraph or section heading.

    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
    ast
    0.91
    or
    0.90
    ar
    0.86
    to
    0.83
    することで
    0.81
    𝘆
    0.80
    pt
    0.79
    を残
    0.79
    𝗮
    0.79
    which
    0.79
    POSITIVE LOGITS
     finishes
    0.77
     inflex
    0.75
    仯
    0.71
    מות
    0.69
     undervalued
    0.68
    硣
    0.67
    ᚐ
    0.66
    ടുത
    0.66
    底下
    0.66
     faceted
    0.66
    Activations Density 0.001%

    No Known Activations