© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11455
    Prev
    Next
    INDEX
    Explanations

    roof repair and roofing work

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

    roof type and inspection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мебели
    0.55
    Furniture
    0.49
     furniture
    0.48
     muebles
    0.47
    ordon
    0.47
    furniture
    0.45
    SqlQuery
    0.44
    ----+
    0.43
     Möbel
    0.43
     мебель
    0.42
    POSITIVE LOGITS
     roof
    2.81
     Roof
    2.67
     roofs
    2.63
    Roof
    2.59
    roof
    2.47
     roofing
    2.31
     rooftops
    2.09
     rooftop
    2.08
     rooft
    2.00
     Roofing
    2.00
    Activations Density 0.374%

    No Known Activations