© 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. 7217
    Prev
    Next
    INDEX
    Explanations

    and conjunctions

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

    This neuron detects specific named entities—proper nouns such as product names, place names, and other capitalized 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
     щоб
    0.74
     ご
    0.70
     キー
    0.68
     電
    0.68
     温度
    0.68
     新作
    0.68
     тобто
    0.67
     人気
    0.66
     つ
    0.66
     ギフト
    0.66
    POSITIVE LOGITS
     and
    1.48
     ਅਤੇ
    1.19
     மற்றும்
    1.16
     आणि
    1.14
     અને
    1.09
    และ
    1.05
     এবং
    1.05
     और
    1.03
     và
    1.00
     एवं
    0.98
    Activations Density 0.001%

    No Known Activations