© 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. 13654
    Prev
    Next
    INDEX
    Explanations

    convolutional neural networks

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

    The neuron fires strongly on the final token of each document/segment, effectively detecting end‐of‐text 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
    ávy
    0.81
    єкт
    0.79
    íny
    0.78
    ě
    0.78
    owały
    0.77
    ায়
    0.76
     प्रत
    0.76
     제외
    0.76
     amortization
    0.76
    ারের
    0.76
    POSITIVE LOGITS
     Communion
    0.77
     fala
    0.75
    晴
    0.73
    言って
    0.73
    )>=
    0.72
     Soma
    0.71
     Cord
    0.71
    为了
    0.71
     ока
    0.71
     Berkeley
    0.70
    Activations Density 0.000%

    No Known Activations