© 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. 45703
    Prev
    Next
    INDEX
    Explanations

    vivid or vividly described

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     senza
    -2.61
     mág
    -2.58
    쿰
    -2.48
    鸲
    -2.45
    卺
    -2.44
    稣
    -2.44
    蟥
    -2.36
     tlie
    -2.22
    ра
    -2.20
    了出来
    -2.20
    POSITIVE LOGITS
    .
    3.14
    Also
    2.72
    that
    2.64
    Five
    2.50
    Only
    2.44
    and
    2.41
    From
    2.36
    ness
    2.34
     而
    2.34
     However
    2.33
    Activations Density 0.002%

    No Known Activations