© 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. 8622
    Prev
    Next
    INDEX
    Explanations

    discussion prompts, persuasion principles, difficult bosses, creative element

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

    The neuron fires strongly on the first substantive word of a new paragraph or section—i.e. tokens that begin distinct text blocks.

    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
    萂
    0.93
    䔧
    0.91
    蕌
    0.91
    茠
    0.91
     inflación
    0.90
     escolares
    0.89
    铁路
    0.88
     дохода
    0.88
    嚶
    0.88
    값이
    0.87
    POSITIVE LOGITS
    ↵
    1.00
    s
    1.00
    al
    0.98
    m
    0.87
    is
    0.75
    elder
    0.74
    om
    0.73
    0.73
    ↵↵
    0.71
     de
    0.71
    Activations Density 0.000%

    No Known Activations