© 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. 9850
    Prev
    Next
    INDEX
    Explanations

    electron science and technology

    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
    y
    -2.52
    </strong>
    -2.47
     According
    -2.30
    箝
    -2.28
     Nevertheless
    -2.28
     інші
    -2.27
    櫚
    -2.25
    泺
    -2.22
    ING
    -2.22
     Meanwhile
    -2.20
    POSITIVE LOGITS
     ''
    2.80
    {
    2.72
    n
    2.66
    2
    2.30
    ଃ
    2.27
     notre
    2.20
     {
    2.16
    瘣
    2.13
    .''
    2.08
     наши
    2.08
    Activations Density 0.010%

    No Known Activations