© 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. 22-GEMMASCOPE-RES-131K
    7. 15542
    Prev
    Next
    INDEX
    Explanations

    pay per click

    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_22/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
     they
    -1.27
     there
    -1.24
     then
    -1.19
     sinistra
    -0.96
     abend
    -0.95
     conferencias
    -0.94
    Produkte
    -0.94
    鄙
    -0.92
     these
    -0.91
    蕯
    -0.91
    POSITIVE LOGITS
     our
    2.52
    我们的
    1.59
    Our
    1.56
     nuestro
    1.52
     unserer
    1.52
     Our
    1.47
     your
    1.45
     unseren
    1.44
    我们
    1.39
     nuestros
    1.34
    Activations Density 0.050%

    No Known Activations