© 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. 12251
    Prev
    Next
    INDEX
    Explanations

    Influence & Community

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

    The neuron fires on domain-specific content words—key nouns and verbs that carry the main topical meaning of a passage.

    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
     reformers
    0.64
     सरकारों
    0.61
    ە
    0.60
    ிர
    0.59
     દ્વારા
    0.59
     milliards
    0.57
     दूरसंचार
    0.57
    }=
    0.57
     galaxies
    0.56
     بواسطة
    0.55
    POSITIVE LOGITS
     এদেশে
    1.14
    ประเทศไทย
    1.04
     aqui
    1.01
     aici
    0.98
     disini
    0.98
     aquí
    0.95
     setempat
    0.95
    氛围
    0.95
    在中
    0.93
     이곳
    0.93
    Activations Density 1.559%

    No Known Activations