© 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. 10-GEMMASCOPE-RES-131K
    7. 128810
    Prev
    Next
    INDEX
    Explanations

    com.example package names

    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
    Not in Any Lists

    No Comments

    Negative Logits
    </h4>
    -1.69
     to
    -1.67
     on
    -1.55
    </h5>
    -1.39
     Könige
    -1.30
     at
    -1.27
     both
    -1.23
     their
    -1.17
     especially
    -1.13
     bijvoorbeeld
    -1.13
    POSITIVE LOGITS
     déchets
    1.38
     lanterna
    1.34
     Chrif
    1.33
     kardashian
    1.33
     aquarelle
    1.32
     marie
    1.31
     bandes
    1.30
     uruguay
    1.30
    窄
    1.27
     Washable
    1.26
    Activations Density 0.127%

    No Known Activations