© 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. 99908
    Prev
    Next
    INDEX
    Explanations

    pillow, cushion, cover

    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
     mob
    -0.84
    گاری
    -0.81
     Friedens
    -0.77
    ือ
    -0.77
    ʖ
    -0.75
     Mob
    -0.73
    kranz
    -0.73
    쁨
    -0.72
    shadowRadius
    -0.72
    鵰
    -0.72
    POSITIVE LOGITS
     pillow
    1.34
     cushion
    1.24
     throw
    1.20
     lumbar
    1.14
     pillows
    1.11
     Pillow
    1.11
     Cushion
    1.09
     zipper
    1.02
     inserts
    0.96
     throws
    0.93
    Activations Density 0.006%

    No Known Activations