© 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. 15677
    Prev
    Next
    INDEX
    Explanations

    hazard, recovery, immunology, earth

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

    The neuron fires strongly on words that occur immediately after a block or sentence break—i.e. on tokens at the beginnings of segments or new paragraphs.

    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
    ี
    0.79
    Voices
    0.74
    Cell
    0.68
     (?)
    0.67
     അല്ലെങ്കിൽ
    0.67
     желания
    0.67
    Que
    0.66
    Sequence
    0.66
    poser
    0.66
    ’’
    0.66
    POSITIVE LOGITS
    𝑫
    0.75
    ্লেখ
    0.72
    邝
    0.70
    给定
    0.70
    化
    0.69
    '.$
    0.69
     eat
    0.68
     paramet
    0.68
    铠
    0.68
    甲
    0.68
    Activations Density 0.000%

    No Known Activations