© 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. 11649
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by UI/navigation boilerplate or “chrome” text (e.g. things like “Read more,” live/tweet indicators, etc.) rather than the core document content.

    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
    pak
    0.63
    mě
    0.63
    OPTV
    0.61
    {
    0.61
    ’
    0.61
    ów
    0.60
    idée
    0.60
    
    0.60
     правда
    0.59
    ם
    0.59
    POSITIVE LOGITS
    ير
    0.61
     Statist
    0.55
    ↵
    0.55
     piani
    0.54
     يصير
    0.53
    ج
    0.53
    Ի
    0.53
    <0x99>
    0.51
    Ս
    0.51
     Ot
    0.50
    Activations Density 1.805%

    No Known Activations