© 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. 3757
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by relatively uncommon, content-heavy words (i.e. lower-frequency tokens) rather than routine or highly frequent function words.

    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
    <unused1896>
    0.37
    <unused292>
    0.37
    <unused320>
    0.37
    <unused520>
    0.37
     ئەو
    0.37
    㡚
    0.36
    <unused350>
    0.36
    <unused327>
    0.36
    <unused528>
    0.35
    <unused569>
    0.35
    POSITIVE LOGITS
    '
    0.51
    ()
    0.46
    ">
    0.45
    +
    0.43
    =
    0.42
    </
    0.39
    ')
    0.39
    ',
    0.38
    </a>
    0.38
    0.37
    Activations Density 1.825%

    No Known Activations