© 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. 114022
    Prev
    Next
    INDEX
    Explanations

    compiler configuration options

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

    configuration settings and compiler options in technical files.

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    _
    -1.30
     \
    -1.30
    \_
    -1.19
     dormitorios
    -1.15
     skill
    -1.15
     here
    -1.13
    Рецепт
    -1.12
    erapeutics
    -1.09
    pub
    -1.07
    gemar
    -1.07
    POSITIVE LOGITS
     They
    1.27
     Städten
    1.20
     Recent
    1.16
    と思って
    1.15
     ois
    1.14
     הכל
    1.13
     状
    1.13
    撣
    1.13
     This
    1.12
     from
    1.11
    Activations Density 0.237%

    No Known Activations