© 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. 7275
    Prev
    Next
    INDEX
    Explanations

    This neuron chiefly responds to proper nouns or named entities (e.g., specific people, places, or organizations).

    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
    س
    0.76
    محمد
    0.66
    ες
    0.66
    கிர
    0.66
    お問い合わせ
    0.64
    સ
    0.64
    Ink
    0.64
    Tucker
    0.63
    Earth
    0.62
    ﺑ
    0.60
    POSITIVE LOGITS
     intang
    0.88
     ohms
    0.84
     shun
    0.84
     depended
    0.80
     refug
    0.80
     championed
    0.80
     linings
    0.80
     educating
    0.79
    ism
    0.78
     никто
    0.78
    Activations Density 1.023%

    No Known Activations