© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107812
    Prev
    Next
    INDEX
    Explanations

    punctuation and quotes

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

    The neuron fires on opening quotation marks that begin quoted passages (with strength roughly proportional to the length of the quoted section).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -1.93
     by
    -1.77
     out
    -1.71
     on
    -1.70
     for
    -1.70
     to
    -1.69
     M
    -1.67
     J
    -1.66
     L
    -1.64
     K
    -1.60
    POSITIVE LOGITS
    ↵↵
    1.63
     poliuret
    1.50
     feltro
    1.43
     innumer
    1.43
     accél
    1.40
     manquer
    1.40
     monaster
    1.39
    
    1.38
     JULIO
    1.37
    蜮
    1.35
    Activations Density 0.016%

    No Known Activations