© 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. 10-GEMMASCOPE-RES-131K
    7. 103475
    Prev
    Next
    INDEX
    Explanations

    plush furnishings and upholstery

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is tuned to detect mentions of upholstery or plush‐fabric materials (e.g. “upholstery,” “plush,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     —
    -2.70
     are
    -2.55
    en
    -2.34
     Of
    -2.28
    on
    -2.28
    in
    -2.17
     OF
    -2.14
    /
    -2.14
    an
    -2.13
     The
    -2.13
    POSITIVE LOGITS
    𓆜
    3.16
    
    2.95
    ᭝
    2.89
    鈇
    2.56
    熜
    2.47
    ༷
    2.44
    Ꭳ
    2.38
    妺
    2.34
    Ꮚ
    2.33
    亖
    2.31
    Activations Density 0.003%

    No Known Activations