© 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. 8196
    Prev
    Next
    INDEX
    Explanations

    FastAPI, Depends, HTTPException

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

    The neuron flags semantically rich “content” words (e.g. technical terms, proper nouns, less frequent nouns/verbs) rather than common function words.

    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
    l
    0.88
     dior
    0.87
     l
    0.80
     BMX
    0.78
     Epson
    0.77
     Teflon
    0.77
     photographic
    0.73
    見る
    0.73
    lable
    0.73
    取る
    0.72
    POSITIVE LOGITS
    министра
    0.78
    ıldığı
    0.76
    Ꮄ
    0.75
     ਤੋਂ
    0.75
     ਸਿੰ
    0.74
    лла
    0.73
     независимо
    0.73
     ਜੋ
    0.73
     ਤੇ
    0.71
     interrupting
    0.70
    Activations Density 0.002%

    No Known Activations