© 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. 39854
    Prev
    Next
    INDEX
    Explanations

    introducing items with "here's a"

    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
    絰
    -1.44
    ynki
    -1.44
    Aww
    -1.42
    糶
    -1.38
     dicono
    -1.38
    imų
    -1.35
     teater
    -1.34
     parlano
    -1.34
     häufigsten
    -1.33
    ynek
    -1.33
    POSITIVE LOGITS
     also
    1.55
     should
    1.55
    ",
    1.50
    ائدة
    1.47
     of
    1.45
     unserem
    1.45
    ”,
    1.39
     but
    1.38
     must
    1.38
     more
    1.34
    Activations Density 0.042%

    No Known Activations