© 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. 16034
    Prev
    Next
    INDEX
    Explanations

    pointers and interfaces

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

    The neuron strongly activates on the first word of a new paragraph or text block, effectively detecting paragraph/section 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
    т
    0.91
    ס
    0.84
    resse
    0.77
    ר
    0.74
    o
    0.73
    as
    0.72
    mä
    0.72
    će
    0.70
    ת
    0.70
    wohl
    0.70
    POSITIVE LOGITS
     Kyrgios
    0.95
     retom
    0.93
     Naira
    0.91
     reimag
    0.90
     torpedo
    0.90
     Patreon
    0.86
     Luffy
    0.85
     HubSpot
    0.85
     Naruto
    0.84
     Nutrient
    0.84
    Activations Density 0.001%

    No Known Activations