© 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. 9640
    Prev
    Next
    INDEX
    Explanations

    Efficiency

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

    The neuron spikes on the last content word of each text block, effectively marking end‐of‐paragraph or section boundary tokens.

    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
    IT
    0.93
    OST
    0.83
    뿅
    0.80
    transactions
    0.78
    AUTH
    0.76
    VOID
    0.75
    짝
    0.75
    AV
    0.75
    ER
    0.74
    ING
    0.74
    POSITIVE LOGITS
     направи
    0.80
     кө
    0.79
    nın
    0.75
    го
    0.75
     Adjusted
    0.72
    ilibus
    0.72
     Portail
    0.71
    头
    0.70
    chrane
    0.70
    日に
    0.69
    Activations Density 0.000%

    No Known Activations