© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 15
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by the character sequence “she,” for example the “she” in “sheer.”

    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
    aitement
    0.79
     ટકા
    0.70
    pero
    0.70
     Wszyst
    0.70
    ͅ
    0.70
     टेक्न
    0.69
    irittura
    0.69
    Toplam
    0.69
    olutamente
    0.67
     അവസ്ഥ
    0.67
    POSITIVE LOGITS
    tors
    0.86
    のス
    0.79
    tabs
    0.78
     Kemal
    0.77
     संस्थानों
    0.75
    ありません
    0.75
    研究院
    0.73
    齐
    0.73
     Gerrard
    0.73
     authoritarian
    0.73
    Activations Density 0.000%

    No Known Activations