© 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. 98910
    Prev
    Next
    INDEX
    Explanations

    organizational units 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
    Negative Logits
     for
    -1.29
     more
    -1.27
    deutschen
    -1.23
    jedno
    -1.20
     âme
    -1.12
    𝐈
    -1.11
    zaron
    -1.11
    ̋
    -1.09
     insanlar
    -1.08
    kurz
    -1.07
    POSITIVE LOGITS
     its
    1.62
     employees
    1.33
    Its
    1.32
     employee
    1.31
     how
    1.30
    velocityX
    1.16
     geprüft
    1.16
    including
    1.14
    Which
    1.12
    zené
    1.12
    Activations Density 0.342%

    No Known Activations