© 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. 13560
    Prev
    Next
    INDEX
    Explanations

    equation parts and symbols

    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
     we
    -2.06
     There
    -1.90
    </h3>
    -1.73
     students
    -1.70
     encontré
    -1.67
     our
    -1.66
     plenty
    -1.64
     llegamos
    -1.60
     various
    -1.60
    %")
    -1.59
    POSITIVE LOGITS
    '
    2.70
    も同じ
    1.77
     respostas
    1.63
    也
    1.56
    也能
    1.53
     {
    1.52
    呜
    1.52
    也在
    1.52
     of
    1.49
     résultats
    1.48
    Activations Density 0.004%

    No Known Activations