© 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. 1248
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly active on the very first content word of 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
    y
    0.89
    top
    0.73
    ine
    0.72
    old
    0.70
    ahan
    0.69
    ócz
    0.68
    ó
    0.67
    amos
    0.67
    d
    0.67
    ly
    0.66
    POSITIVE LOGITS
     залиши
    0.88
     vérifier
    0.86
    愺
    0.86
    ानंतर
    0.79
     मायणी
    0.78
    റിന്റെ
    0.78
    ❰
    0.78
     astrocyte
    0.77
    䛊
    0.77
     subpo
    0.77
    Activations Density 0.005%

    No Known Activations