© 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. 68183
    Prev
    Next
    INDEX
    Explanations

    as well as

    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
     one
    -2.11
     it
    -1.90
    lamó
    -1.77
     jovial
    -1.73
     where
    -1.69
     désolés
    -1.65
     different
    -1.62
     there
    -1.59
     two
    -1.57
    ？（
    -1.55
    POSITIVE LOGITS
    </h4>
    1.87
     also
    1.80
     mortos
    1.63
     tohto
    1.59
     geïsole
    1.58
    ⩖
    1.58
    nipeg
    1.57
     stöd
    1.57
     zacht
    1.55
    amna
    1.54
    Activations Density 0.050%

    No Known Activations