© 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. 7324
    Prev
    Next
    INDEX
    Explanations

    GitHub, Python, Node.js, Wayland

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

    This neuron detects paragraph breaks or empty-line separators in the text.

    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
    朢
    0.68
     two
    0.64
     three
    0.63
     tiga
    0.63
    两个
    0.61
     التى
    0.61
     zwei
    0.59
     तीन
    0.59
     três
    0.58
    兩個
    0.58
    POSITIVE LOGITS
    ämän
    0.54
    ἀ
    0.52
     yǐ
    0.51
    ಣ್ಣ
    0.50
    łożyć
    0.50
     Thereby
    0.49
    Fullscreen
    0.49
    ін
    0.48
    ⟶
    0.48
    ્
    0.47
    Activations Density 0.467%

    No Known Activations