© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 3512
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on ranking-style or promotional header terms (e.g. “Best,” “match,” “results,” “relevance”) indicating top-list or top-rank context.

    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
    !'
    0.84
    ?'
    0.79
    cology
    0.77
    le
    0.77
    '!
    0.73
    !"
    0.72
     Jupyter
    0.71
    %:
    0.71
    !
    0.71
    !’
    0.71
    POSITIVE LOGITS
     geeign
    0.65
     ஒன்றாக
    0.64
    akat
    0.64
     подходя
    0.64
    обходи
    0.63
     بعض
    0.63
    ices
    0.62
    াজের
    0.62
     যেটি
    0.62
    substituted
    0.61
    Activations Density 0.000%

    No Known Activations