© 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. 129370
    Prev
    Next
    INDEX
    Explanations

    be seated on or in

    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
     walk
    -1.30
     walking
    -1.13
     walks
    -1.09
    walk
    -1.04
    Припев
    -0.98
    ショナル
    -0.93
     day
    -0.92
    یزات
    -0.91
    Walk
    -0.90
    站在
    -0.90
    POSITIVE LOGITS
     sitting
    1.39
     seated
    1.38
    seated
    1.30
     seating
    1.25
     sentado
    1.25
     ngồi
    1.22
    sitting
    1.20
     seats
    1.10
     table
    1.10
    Sitting
    1.08
    Activations Density 0.039%

    No Known Activations