© 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. 68742
    Prev
    Next
    INDEX
    Explanations

    a blog post

    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
    Forgery
    -1.50
    ným
    -1.35
    Seni
    -1.34
     zelf
    -1.33
    Useless
    -1.32
    גע
    -1.29
    Filmography
    -1.29
    assertj
    -1.28
    הג
    -1.27
    cestors
    -1.22
    POSITIVE LOGITS
    including
    1.37
    you
    1.30
    」
    1.29
                    
    1.27
     You
    1.22
    ）
    1.18
    】：
    1.17
    　
    1.17
    _
    1.17
    Studies
    1.16
    Activations Density 0.103%

    No Known Activations