© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9482
    Prev
    Next
    INDEX
    Explanations

    issue, profit, specific details

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

    The neuron strongly responds to words indicating relative position or sequence (e.g. “middle,” “top,” “first,” “plurality”).

    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
    շ
    0.76
    도는
    0.76
    に残
    0.73
    Forg
    0.73
    Shut
    0.70
    भूति
    0.69
    器材
    0.69
    صة
    0.68
     Mercur
    0.68
     magnetism
    0.68
    POSITIVE LOGITS
    ায়ন
    0.86
    англ
    0.81
     dàng
    0.76
     SOCK
    0.73
     лес
    0.72
    ;<
    0.71
    噼
    0.70
    🍥
    0.70
     тоді
    0.69
    喻
    0.68
    Activations Density 0.000%

    No Known Activations