© 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. 68665
    Prev
    Next
    INDEX
    Explanations

    return values or expressions

    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
    /**
    -1.46
    ///
    -1.42
     butik
    -1.39
    \
    -1.38
    always
    -1.31
    another
    -1.31
    //
    -1.29
     />
    -1.27
     другую
    -1.27
    ү
    -1.24
    POSITIVE LOGITS
     their
    1.81
     on
    1.48
    に行ってきました
    1.38
     Pristup
    1.37
     komunikasi
    1.33
     también
    1.30
     objav
    1.26
     with
    1.23
    他們的
    1.23
     їх
    1.21
    Activations Density 0.001%

    No Known Activations