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

    Neuronpedia

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

    The neuron fires on personal names in academic-style citations (i.e. authors’ last 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
    Bible
    0.19
    Soviet
    0.18
    Bibliography
    0.18
    BBC
    0.17
    memorial
    0.17
    Memorial
    0.17
    ©
    0.17
    Founder
    0.17
    ®
    0.17
    Film
    0.16
    POSITIVE LOGITS
     xWidth
    0.19
    <unused345>
    0.18
     κον
    0.18
     рекомендуется
    0.18
     BlueprintName
    0.18
     dailySales
    0.17
     Ши
    0.17
     Inoltre
    0.17
    <unused333>
    0.17
     являются
    0.17
    Activations Density 0.302%

    No Known Activations