© 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. 26247
    Prev
    Next
    INDEX
    Explanations

    Riemannian manifold

    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
     herbes
    -1.02
     luks
    -1.00
     minimalis
    -1.00
     behar
    -0.99
     zan
    -0.96
     geograf
    -0.95
     fabrik
    -0.94
     formules
    -0.94
     engelsk
    -0.94
     تصميم
    -0.94
    POSITIVE LOGITS
     while
    1.34
     with
    1.21
     students
    1.20
     quickly
    1.15
     although
    1.14
     oftentimes
    1.13
     for
    1.10
     because
    1.07
     rápidamente
    1.06
     wildly
    1.06
    Activations Density 0.007%

    No Known Activations