© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8962
    Prev
    Next
    INDEX
    Explanations

    text or code delimiters

    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
     but
    -1.77
     such
    -1.58
     таких
    -1.38
    czyć
    -1.34
     particularly
    -1.30
     moreover
    -1.30
    ⅞
    -1.29
     new
    -1.28
     especially
    -1.26
    евич
    -1.23
    POSITIVE LOGITS
    '
    1.23
     спеціаль
    1.23
     vierge
    1.22
    了不少
    1.22
    了两
    1.22
    ate
    1.22
     család
    1.21
    攢
    1.21
    section
    1.20
    Примі
    1.20
    Activations Density 0.106%

    No Known Activations