© 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. 115804
    Prev
    Next
    INDEX
    Explanations

    interior home spaces

    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
     Ос
    -0.88
     conhecida
    -0.83
     Roofing
    -0.82
    ἐ
    -0.80
    ἃ
    -0.79
    鄚
    -0.79
     盤
    -0.78
    roof
    -0.78
    ἔ
    -0.77
     знаем
    -0.76
    POSITIVE LOGITS
     home
    1.38
     interiors
    1.36
     interior
    1.26
     homes
    1.25
     room
    1.23
     decor
    1.20
     rooms
    1.18
     living
    1.14
     themed
    1.13
     space
    1.12
    Activations Density 0.035%

    No Known Activations