© 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. 9181
    Prev
    Next
    INDEX
    Explanations

    This neuron selectively responds to capitalized proper nouns and named entities (e.g., personal names, titles, brand names, and other named terms).

    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
    '
    0.97
    IST
    0.95
     spécial
    0.92
    ATE
    0.91
     nationalist
    0.89
     toning
    0.88
     tặng
    0.87
    ’
    0.85
    なんと
    0.85
    IA
    0.84
    POSITIVE LOGITS
    dır
    1.45
    ه‌
    1.26
    www
    1.16
    fono
    1.16
    nbhost
    1.15
    larda
    1.14
    های
    1.13
    هُ
    1.13
    nja
    1.12
    youtu
    1.11
    Activations Density 23.383%

    No Known Activations