© 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. 10-GEMMASCOPE-RES-131K
    7. 99011
    Prev
    Next
    INDEX
    Explanations

    read more

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

    This neuron detects prompts or links inviting the reader to continue or expand the content (e.g. “read more,” “see full summary,” “continue reading”).

    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
     of
    -2.73
     on
    -2.09
    しますが
    -1.69
     method
    -1.52
    したもの
    -1.49
    Every
    -1.48
    7
    -1.45
     When
    -1.43
     at
    -1.41
    するので
    -1.38
    POSITIVE LOGITS
     ۱۸
    1.63
     ۱۵
    1.52
    这
    1.49
    漂亮
    1.49
     mogą
    1.45
     leitura
    1.45
    蜮
    1.45
    素晴らしい
    1.44
    acionales
    1.44
     ۱۹
    1.42
    Activations Density 0.022%

    No Known Activations