© 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. 10862
    Prev
    Next
    INDEX
    Explanations

    state your opinion

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

    The neuron fires on tokens that appear as section headings or labels (e.g. “people,” “information,” “what,” “is”) in structured/legal-style text.

    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
     giây
    0.73
    сен
    0.72
    וג
    0.71
     surfaced
    0.70
    ش
    0.68
     apiUrl
    0.67
    لع
    0.66
    𠃍
    0.66
    נק
    0.65
    អារ
    0.65
    POSITIVE LOGITS
     пыта
    0.98
     выполня
    0.96
     estar
    0.91
     toekom
    0.91
     únicamente
    0.88
    ours
    0.86
     entender
    0.86
     tiveram
    0.86
     выпол
    0.84
     estimados
    0.84
    Activations Density 0.001%

    No Known Activations