© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50477
    Prev
    Next
    INDEX
    Explanations

    buildings and vegetation

    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
    летний
    -0.93
    ädie
    -0.81
    )))),
    -0.80
    ictionary
    -0.78
    课堂
    -0.77
     badkamer
    -0.77
     Ungarn
    -0.76
    teries
    -0.74
    ündigen
    -0.73
    Chooser
    -0.73
    POSITIVE LOGITS
     trees
    3.89
     buildings
    3.39
     houses
    2.84
    trees
    2.75
     tree
    2.64
     Trees
    2.47
    Trees
    2.44
     bushes
    2.23
    buildings
    2.19
     vegetation
    2.17
    Activations Density 0.074%

    No Known Activations