© 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. 10829
    Prev
    Next
    INDEX
    Explanations

    dialogue or example sentence start

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

    The neuron strongly responds to the main headword being defined in dictionary‐style entries.

    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
    NO
    0.60
    M
    0.60
     इसलिए
    0.57
    Chars
    0.57
    hhhh
    0.57
    uuuu
    0.57
    ON
    0.56
    hhh
    0.56
    O
    0.56
     เลย
    0.56
    POSITIVE LOGITS
     bisogna
    0.57
     dès
    0.55
     alas
    0.54
     crook
    0.54
     fuga
    0.54
     angiography
    0.54
     stifle
    0.52
     অসহ
    0.52
     adjunction
    0.52
     queer
    0.52
    Activations Density 0.011%

    No Known Activations