© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 83728
    Prev
    Next
    INDEX
    Explanations

    frowning cant, her pictures, big buzz

    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
    -1.88
     to
    -1.78
    着一个
    -1.70
     as
    -1.59
     on
    -1.41
     by
    -1.41
    着一
    -1.40
     which
    -1.34
     of
    -1.30
    きたいと思います
    -1.27
    POSITIVE LOGITS
     tandis
    1.60
     naviguant
    1.45
     adesi
    1.41
    </h2>
    1.36
    </b>
    1.34
     others
    1.30
     czuj
    1.30
     Fähigkeit
    1.28
     grossa
    1.27
    仝
    1.27
    Activations Density 0.009%

    No Known Activations