© 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. 67835
    Prev
    Next
    INDEX
    Explanations

    what it is like

    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
     célè
    -1.84
     devenue
    -1.75
    èvent
    -1.67
    陬
    -1.66
    /}{
    -1.61
    iphery
    -1.59
     géant
    -1.56
    ătate
    -1.55
    鹪
    -1.55
     odeur
    -1.54
    POSITIVE LOGITS
     how
    1.88
     because
    1.74
    ’
    1.66
     when
    1.62
     this
    1.61
    …」
    1.61
     each
    1.56
     even
    1.52
     instead
    1.52
     all
    1.49
    Activations Density 0.023%

    No Known Activations