© 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. 21115
    Prev
    Next
    INDEX
    Explanations

    ratios

    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
     When
    -3.09
     There
    -3.00
    {
    -2.95
    when
    -2.59
     Those
    -2.45
     cheerful
    -2.38
    to
    -2.36
     if
    -2.31
     Shortly
    -2.31
     nine
    -2.30
    POSITIVE LOGITS
     ‚
    2.83
     sabias
    2.75
    粜
    2.72
     specif
    2.69
    跸
    2.59
     è
    2.56
     dando
    2.55
     praktische
    2.52
     imprescin
    2.50
    荭
    2.47
    Activations Density 0.054%

    No Known Activations