© 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. 22-GEMMASCOPE-RES-131K
    7. 16661
    Prev
    Next
    INDEX
    Explanations

    gratitude for gifts and kindness

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     or
    -0.98
     at
    -0.97
     as
    -0.95
     on
    -0.90
     in
    -0.87
    pstmt
    -0.84
    larımız
    -0.83
     interessanti
    -0.79
     Gouvernement
    -0.79
     ods
    -0.78
    POSITIVE LOGITS
     thank
    1.41
     generosity
    1.41
     gifts
    1.39
     gracious
    1.39
     Thank
    1.39
     gift
    1.35
     generous
    1.32
     thanked
    1.24
     grateful
    1.20
     thanks
    1.20
    Activations Density 0.044%

    No Known Activations