© 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. 14591
    Prev
    Next
    INDEX
    Explanations

    factors, concerns, weight

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

    This neuron responds to document-structure tokens that mark section headings or subsection labels.

    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
    illy
    0.82
     maî
    0.75
    speak
    0.71
     이슈
    0.69
     시간에
    0.68
    飧
    0.68
     शशि
    0.68
    目
    0.67
    می
    0.67
     lutter
    0.67
    POSITIVE LOGITS
     eléctricos
    0.80
    hia
    0.80
     अफसरों
    0.75
     eléctrico
    0.74
     производителей
    0.72
     Франции
    0.71
     geométricas
    0.70
    Referencias
    0.69
    arde
    0.69
     electrified
    0.68
    Activations Density 0.000%

    No Known Activations