© 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. 2715
    Prev
    Next
    INDEX
    Explanations

    listing items or sections

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

    This neuron fires most strongly on the last substantive token at the end of each text chunk, effectively marking segment or paragraph boundaries.

    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
     crappy
    0.73
     fakat
    0.69
     namelijk
    0.66
    めっちゃ
    0.65
     ಎಲ್ಲಾ
    0.63
     근데
    0.63
     Ι
    0.62
     unassuming
    0.62
     ContentView
    0.62
    理
    0.62
    POSITIVE LOGITS
    ."
    0.88
    .)
    0.88
    ).
    0.84
    .”
    0.82
    ——
    0.82
    .")
    0.77
    も見
    0.75
    ."))
    0.74
    .).
    0.73
    ‌.
    0.72
    Activations Density 0.044%

    No Known Activations