© 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. 15598
    Prev
    Next
    INDEX
    Explanations

    programming and technical terms

    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
     have
    -2.34
    图为
    -2.08
    两年
    -2.08
    锂
    -2.03
     dearest
    -2.03
    饺子
    -2.02
     nifty
    -2.02
     \
    -1.92
    ᯾
    -1.89
     Filho
    -1.88
    POSITIVE LOGITS
     continúas
    2.63
     accentu
    2.38
    鼱
    2.36
     proclaims
    2.33
    '
    2.28
    媖
    2.27
     expresses
    2.22
     underlines
    2.20
    ?”
    2.16
     únicamente
    2.14
    Activations Density 0.001%

    No Known Activations