© 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. 34-GEMMASCOPE-RES-131K
    7. 63240
    Prev
    Next
    INDEX
    Explanations

    chair roles and titles

    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_34/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
     występu
    -1.03
    longed
    -1.02
     terdapat
    -0.91
     encontrar
    -0.91
    ってる
    -0.91
     теми
    -0.89
     spectacular
    -0.89
    趴
    -0.87
     ใน
    -0.87
     kèo
    -0.86
    POSITIVE LOGITS
    persons
    1.33
    woman
    1.28
     Chair
    1.19
     CHAIR
    1.11
    🪑
    1.04
    Chair
    1.01
    🌹
    0.96
    lift
    0.95
     Chairs
    0.93
    獁
    0.93
    Activations Density 0.009%

    No Known Activations