© 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. 15411
    Prev
    Next
    INDEX
    Explanations

    foreign-language and cultural terms

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

    The neuron fires on multi-syllable proper names and specialized named entities (e.g. place names, personal names, terms in other languages).

    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
    AcOH
    0.30
    eduanya
    0.30
     NSLog
    0.29
    UIAlert
    0.29
    ennzeichnet
    0.29
    ITLE
    0.29
    ushchev
    0.28
    ﺎ
    0.28
    šenja
    0.28
    asyarakat
    0.27
    POSITIVE LOGITS
    -
    0.41
     locale
    0.27
     topl
    0.27
     seamless
    0.26
     cultivar
    0.26
    /
    0.26
     type
    0.25
     theater
    0.25
     alebo
    0.25
    ↵
    0.25
    Activations Density 0.026%

    No Known Activations