© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9729
    Prev
    Next
    INDEX
    Explanations

    (hopefully!) easy to understand

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is highly sensitive to open‐parenthesis tokens that introduce parenthetical citations or numeric references.

    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
    0.67
    M
    0.65
    Maurice
    0.63
     such
    0.63
    Imp
    0.62
    Vida
    0.61
    Such
    0.61
    K
    0.59
    Mo
    0.59
    Ch
    0.58
    POSITIVE LOGITS
     vagy
    0.78
    ﷻ
    0.73
    !!)
    0.71
    hopefully
    0.71
     verseny
    0.68
     экономи
    0.68
    JScripts
    0.67
     робо
    0.66
    ！）
    0.66
     usu
    0.66
    Activations Density 0.029%

    No Known Activations