© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 55806
    Prev
    Next
    INDEX
    Explanations

    chair parts and furniture

    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
    LÄ
    -0.85
     nằm
    -0.82
    macros
    -0.81
     Estadual
    -0.80
    cuencia
    -0.79
     aDecoder
    -0.76
    Ход
    -0.75
    ToAction
    -0.75
    urbo
    -0.74
     tava
    -0.74
    POSITIVE LOGITS
     chair
    1.86
     chairs
    1.82
     Chair
    1.59
     Chairs
    1.48
    chair
    1.40
    Chair
    1.34
     sillas
    1.27
     CHAIR
    1.17
    chairs
    1.11
     stack
    1.10
    Activations Density 0.013%

    No Known Activations