© 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. 59680
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript code snippets

    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
     either
    -1.84
     but
    -1.57
    穑
    -1.47
    ϐ
    -1.44
     construido
    -1.43
     encantador
    -1.41
     explicado
    -1.41
    手指
    -1.40
     zonder
    -1.36
     eficiente
    -1.35
    POSITIVE LOGITS
    some
    1.84
     they
    1.72
    .
    1.66
     with
    1.63
    옳
    1.62
    ups
    1.55
    only
    1.50
     kimi
    1.48
    which
    1.48
    although
    1.45
    Activations Density 0.012%

    No Known Activations