© 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. 2036
    Prev
    Next
    INDEX
    Explanations

    The neuron is keyed to tokens that occur at the ends of lines or blocks—that is, it fires on the final token in a line.

    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
    ழிவு
    0.63
    udz
    0.59
    simmons
    0.59
    foregroundView
    0.58
     গিয়ে
    0.57
    𝘺
    0.55
    લિક
    0.54
     dataGenerator
    0.54
    டைந்து
    0.54
    assel
    0.53
    POSITIVE LOGITS
    sthe
    0.84
    es
    0.75
    as
    0.74
    斯的
    0.72
     that
    0.60
    at
    0.59
    ↵
    0.59
    m
    0.59
    斯
    0.59
    u
    0.57
    Activations Density 0.036%

    No Known Activations