© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7878
    Prev
    Next
    INDEX
    Explanations

    " quotation mark followed by sentence start

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

    The neuron detects opening quotation‐mark tokens signaling the start of quoted speech.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ”,
    -1.78
     menggambarkan
    -1.70
    $
    -1.69
     exquisite
    -1.67
    ........
    -1.66
     также
    -1.66
     एवं
    -1.66
    Since
    -1.59
    .......
    -1.58
     этим
    -1.57
    POSITIVE LOGITS
    是一款
    1.83
     his
    1.68
    쑹
    1.66
     garantis
    1.56
    紲
    1.55
    
    1.53
    ：
    1.52
     evangé
    1.52
     raiſ
    1.50
    禟
    1.49
    Activations Density 0.007%

    No Known Activations