© 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. 5203
    Prev
    Next
    INDEX
    Explanations

    service type or action

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

    This neuron selectively activates on unusually long or multi-syllabic tokens (often technical or compound 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
    γγελμα
    0.52
    iney
    0.49
     हर्षवर्धन
    0.48
    〟
    0.47
     docentes
    0.47
     radicals
    0.46
    ruptcy
    0.46
     второго
    0.46
    yscraper
    0.46
     увиде
    0.46
    POSITIVE LOGITS
     ಯಾವಾಗ
    0.56
    始终
    0.55
     Ростов
    0.52
    处理
    0.51
    經常
    0.51
    允许
    0.51
     எப்போதும்
    0.50
    処理
    0.49
    システム
    0.48
    ពេល
    0.48
    Activations Density 0.000%

    No Known Activations