© 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. 647
    Prev
    Next
    INDEX
    Explanations

    This neuron selectively fires for capitalized named entities, especially personal names.

    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
     outperformed
    0.41
    💋
    0.41
     էր
    0.40
    💆
    0.40
    वासियों
    0.40
    Პ
    0.39
    🧂
    0.38
     overpowered
    0.38
    вала
    0.37
     increí
    0.37
    POSITIVE LOGITS
    on
    0.52
    it
    0.52
    ie
    0.47
    ع
    0.43
     Family
    0.40
     Study
    0.40
    ز
    0.40
    ON
    0.38
    at
    0.38
     family
    0.38
    Activations Density 0.000%

    No Known Activations