© 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. 65548
    Prev
    Next
    INDEX
    Explanations

    what they describe

    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
     is
    -1.01
    WHERE
    -1.01
     puisqu
    -0.96
    пенно
    -0.94
    é
    -0.93
    lig
    -0.91
     xiao
    -0.91
    ḻ
    -0.90
     Elé
    -0.90
     Là
    -0.89
    POSITIVE LOGITS
     their
    2.23
     they
    1.71
     themselves
    1.57
     would
    1.43
    各自
    1.32
     swoich
    1.26
     thier
    1.24
     różnych
    1.23
     zlep
    1.17
     about
    1.16
    Activations Density 0.059%

    No Known Activations