© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79249
    Prev
    Next
    INDEX
    Explanations

    questions about code and circuits

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

    The neuron is detecting spans of direct quoted speech (text enclosed in quotation marks).

    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
     emphasizing
    -1.02
    camis
    -0.99
    cartier
    -0.90
     regarded
    -0.89
     getting
    -0.87
    chaise
    -0.86
     since
    -0.86
     might
    -0.85
    collier
    -0.83
     insisting
    -0.82
    POSITIVE LOGITS
    ㆍ
    1.16
    bly
    1.02
    BF
    1.02
    Sport
    1.02
    src
    1.02
    direct
    1.01
     ſie
    1.01
     ','
    1.01
     '/')
    1.00
    őség
    1.00
    Activations Density 0.006%

    No Known Activations