© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7820
    Prev
    Next
    INDEX
    Explanations

    hugging face, hu, hunched

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

    This neuron detects capitalized named entities—proper nouns referring to people or places.

    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_31_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
     Died
    0.61
    NSArray
    0.57
    icals
    0.56
     retali
    0.56
    RENDER
    0.55
    燚
    0.55
     ganz
    0.54
    ভারতীয়
    0.54
     entire
    0.53
    entire
    0.53
    POSITIVE LOGITS
     HU
    0.89
     ху
    0.72
     Ху
    0.68
     Hu
    0.68
    륭
    0.67
    HU
    0.65
    Hu
    0.65
     hu
    0.63
     胡
    0.63
    bner
    0.63
    Activations Density 0.239%

    No Known Activations