© 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. 129064
    Prev
    Next
    INDEX
    Explanations

    contrast after but

    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
     to
    -2.03
    ),
    -1.70
     if
    -1.59
    )$
    -1.58
    %)
    -1.44
     If
    -1.41
    %),
    -1.37
     its
    -1.36
     \%)$
    -1.34
     more
    -1.32
    POSITIVE LOGITS
     errone
    1.70
     relojes
    1.42
     cordones
    1.41
     agujeros
    1.40
     impe
    1.38
     tiroirs
    1.38
     stiefel
    1.38
     vya
    1.37
     then
    1.37
     vasto
    1.34
    Activations Density 0.155%

    No Known Activations