© 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. 15086
    Prev
    Next
    INDEX
    Explanations

    user prompts, instructions, or input

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

    This neuron detects the “###” section-heading markers (markdown-style headings) in the text.

    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
    其
    0.77
    0.75
    та
    0.70
    FlatAppearance
    0.69
    エー
    0.67
    в
    0.66
    平
    0.66
    PhysRev
    0.65
    ฟ้า
    0.64
    ro
    0.62
    POSITIVE LOGITS
    grateful
    0.94
    quirements
    0.91
    dfunding
    0.87
    檎
    0.86
    𝑜
    0.86
     Balliye
    0.85
     वेगवेग
    0.83
    𝕠
    0.83
    aring
    0.82
     açúcar
    0.82
    Activations Density 0.000%

    No Known Activations