© 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. 71373
    Prev
    Next
    INDEX
    Explanations

    some noun

    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
    ⚣
    -1.64
     répondre
    -1.59
     că
    -1.56
    ౬
    -1.52
    ie
    -1.49
     juiste
    -1.45
     electrónica
    -1.45
    uk
    -1.42
     gérer
    -1.41
     envía
    -1.41
    POSITIVE LOGITS
    These
    2.03
     from
    1.74
    沨
    1.70
     Clearly
    1.59
     Both
    1.59
     Consequently
    1.59
    jarah
    1.55
     such
    1.55
    Those
    1.54
    Both
    1.50
    Activations Density 0.054%

    No Known Activations