© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3592
    Prev
    Next
    INDEX
    Explanations

    short term

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

    This neuron activates strongly on the very first meaningful word of a new sentence or text segment.

    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
     Lehenga
    0.91
    оны
    0.86
    ড়ি
    0.86
    Ы
    0.83
    ড়ি
    0.82
    сцю
    0.82
     Tires
    0.82
    ジ
    0.81
     floribus
    0.79
    ўкі
    0.77
    POSITIVE LOGITS
     priority
    0.66
    n
    0.65
     waktu
    0.61
     partis
    0.61
    wss
    0.61
    <0x80>
    0.58
    वय
    0.58
    >//
    0.57
     future
    0.57
     action
    0.56
    Activations Density 0.001%

    No Known Activations