© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66015
    Prev
    Next
    INDEX
    Explanations

    actions completed by others

    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
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -2.14
     never
    -1.03
     )
    -1.03
    </strong>
    -1.02
    ),
    -0.93
     &
    -0.91
     gently
    -0.90
     バター
    -0.90
     >
    -0.89
     then
    -0.88
    POSITIVE LOGITS
     by
    1.77
    everyone
    1.34
     beaucoup
    1.24
     Geheimnis
    1.21
     indiví
    1.19
    Largeur
    1.19
    oleh
    1.15
     everyone
    1.15
     всеми
    1.13
    
    1.09
    Activations Density 0.093%

    No Known Activations