© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1704
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on standalone section‐header or topic‐label words (e.g. “Metropolitan,” “Area,” “Space,” “Signs”) that introduce or title a new part of 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
    u
    0.93
    એ
    0.79
    de
    0.75
    на
    0.71
    a
    0.71
    ɰ
    0.71
    效率
    0.69
    やっと
    0.68
    在
    0.67
    返
    0.67
    POSITIVE LOGITS
     Sacrament
    0.77
    dures
    0.75
    SystemColors
    0.74
     tracheal
    0.73
    قيم
    0.71
    ElementSibling
    0.71
     DAYS
    0.70
     freestanding
    0.69
    PARAMETER
    0.69
    romyalgia
    0.69
    Activations Density 0.000%

    No Known Activations