© 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. 11731
    Prev
    Next
    INDEX
    Explanations

    following prepositions and conjunctions

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

    The neuron strongly activates on long, multi-syllable, domain-specific content words—especially technical nouns.

    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
    拵
    0.79
     solamente
    0.75
     sólo
    0.71
    avec
    0.71
    lieu
    0.70
     Choir
    0.70
    enriched
    0.67
    with
    0.66
    含む
    0.66
     notably
    0.65
    POSITIVE LOGITS
     丨
    0.94
     hahaha
    0.93
     netizens
    0.88
     vasodilator
    0.88
     hyperglycemia
    0.86
     Bundan
    0.86
     keto
    0.85
     Haha
    0.84
     haha
    0.83
     Xiaomi
    0.82
    Activations Density 0.188%

    No Known Activations