© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76797
    Prev
    Next
    INDEX
    Explanations

    curtain or veil

    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
     lg
    -0.80
    合って
    -0.77
    ACS
    -0.76
    hlt
    -0.75
     spirals
    -0.74
    GPI
    -0.73
     wp
    -0.73
    尖
    -0.72
    Bridges
    -0.72
     設計
    -0.72
    POSITIVE LOGITS
     curtain
    3.56
     curtains
    3.56
     Curtain
    2.64
     Curtains
    2.55
     cortinas
    1.98
    カーテン
    1.87
     drapes
    1.83
     cortina
    1.70
    Cur
    1.65
     veil
    1.52
    Activations Density 0.015%

    No Known Activations