© 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. 67634
    Prev
    Next
    INDEX
    Explanations

    scientific notation and units

    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
     может
    -1.47
     étapes
    -1.45
     на
    -1.37
     雑誌
    -1.36
    </em>
    -1.35
    </h4>
    -1.35
     communautés
    -1.33
    慢慢
    -1.30
     then
    -1.28
     THERE
    -1.28
    POSITIVE LOGITS
     in
    1.64
    ies
    1.48
     tegens
    1.41
    AfterViewInit
    1.41
     весна
    1.41
    urium
    1.39
    さみ
    1.36
     zelve
    1.36
    verns
    1.35
     promesse
    1.35
    Activations Density 0.095%

    No Known Activations