© 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. 72051
    Prev
    Next
    INDEX
    Explanations

    musical instruments and technology

    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
    Not in Any Lists

    No Comments

    Negative Logits
     навіть
    -1.48
     aseguró
    -1.34
     detalló
    -1.31
     была
    -1.30
     даже
    -1.28
    Even
    -1.26
    ilustrasi
    -1.23
     виправи
    -1.21
     zelfs
    -1.21
     system
    -1.21
    POSITIVE LOGITS
     nimi
    1.30
     etui
    1.18
    во
    1.17
    rogate
    1.14
    熥
    1.13
    примеча
    1.11
     mies
    1.10
     entrambi
    1.09
     thiệu
    1.09
    ces
    1.09
    Activations Density 0.058%

    No Known Activations