© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14187
    Prev
    Next
    INDEX
    Explanations

    participating in

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

    The neuron detects sentence-final boundaries, i.e. the ends of sentences marked by punctuation (periods, exclamation points, etc.).

    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
    い
    0.93
    ل
    0.92
     Helpline
    0.89
    م
    0.87
     roared
    0.85
    电视剧
    0.84
     História
    0.83
     Destroyer
    0.82
     Fears
    0.81
    小说
    0.80
    POSITIVE LOGITS
    plas
    0.84
    pag
    0.78
    effectiveness
    0.78
    reg
    0.77
    sen
    0.77
    sal
    0.77
    neg
    0.77
    QUAL
    0.75
    $-\
    0.75
    rt
    0.74
    Activations Density 0.000%

    No Known Activations