© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12535
    Prev
    Next
    INDEX
    Explanations

    construction and technical terms

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

    This neuron detects the first substantive token at the start of a new paragraph or section.

    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
    s
    1.04
    adon
    0.93
    س
    0.88
    abolic
    0.87
    kannya
    0.87
    ARD
    0.86
    मधील
    0.86
    saus
    0.85
     sebagaimana
    0.85
     appuy
    0.82
    POSITIVE LOGITS
     seasoned
    0.85
     आउटफिट
    0.77
     Руси
    0.77
    ップ
    0.74
    픈
    0.72
    ंसिल
    0.66
     বঙ্গের
    0.66
     Controle
    0.66
    ခြား
    0.66
     Результа
    0.66
    Activations Density 0.000%

    No Known Activations