© 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. 26611
    Prev
    Next
    INDEX
    Explanations

    how to or why topics

    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
    ridas
    -0.99
     espèces
    -0.99
    あら
    -0.97
    頑張って
    -0.97
     réaction
    -0.96
     Estas
    -0.93
    ではでは
    -0.90
     эту
    -0.88
    illeurs
    -0.88
    žová
    -0.88
    POSITIVE LOGITS
     and
    1.43
     new
    1.09
     which
    1.00
     so
    1.00
    胄
    1.00
    new
    0.97
     What
    0.95
    しましたが
    0.95
     Why
    0.95
     How
    0.95
    Activations Density 0.031%

    No Known Activations