© 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. 85467
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

    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
    %;
    -1.89
     “
    -1.81
    <blockquote>
    -1.77
    },
    -1.77
     now
    -1.75
    </h3>
    -1.65
    }{
    -1.59
     on
    -1.56
    Now
    -1.55
     use
    -1.54
    POSITIVE LOGITS
     willen
    1.58
     kapak
    1.52
    ௜
    1.47
     ation
    1.46
    Архівовано
    1.45
    ってみました
    1.45
     dekoratif
    1.44
     cok
    1.41
     incontra
    1.41
     hadden
    1.40
    Activations Density 0.031%

    No Known Activations