© 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. 25499
    Prev
    Next
    INDEX
    Explanations

    usual/typical contexts

    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
    Cited
    -1.09
    backers
    -1.07
    ində
    -0.95
    ergies
    -0.94
     -¿
    -0.93
    曲を
    -0.92
    ADDRESS
    -0.91
    шкина
    -0.90
     البرنامج
    -0.89
    verteilung
    -0.87
    POSITIVE LOGITS
     usual
    1.95
     typical
    1.88
    usual
    1.64
     típico
    1.55
    typical
    1.47
     típica
    1.41
    いつもの
    1.38
     customary
    1.30
     typically
    1.23
     Usual
    1.23
    Activations Density 0.132%

    No Known Activations