© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107759
    Prev
    Next
    INDEX
    Explanations

    outdoor shades and awnings

    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
     aço
    -0.83
     gentleman
    -0.71
    󠁣
    -0.70
     moza
    -0.69
     Anat
    -0.69
    Shared
    -0.69
     circulaire
    -0.69
    CONTENIDO
    -0.69
     share
    -0.68
     nœ
    -0.68
    POSITIVE LOGITS
     awning
    1.90
     awn
    1.90
     Aw
    1.45
    Aw
    1.34
     cassette
    1.05
     sunscreen
    1.04
    wn
    1.02
     retractable
    1.02
     fabrics
    0.97
     patio
    0.95
    Activations Density 0.010%

    No Known Activations