© 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. 98266
    Prev
    Next
    INDEX
    Explanations

    deciduous shrub

    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
     Botanic
    -0.78
     planta
    -0.77
     Pflanzen
    -0.75
    Vegetation
    -0.71
    savevideo
    -0.71
     Vegetation
    -0.69
    銆
    -0.69
    veget
    -0.66
     botanist
    -0.66
     Veget
    -0.65
    POSITIVE LOGITS
     trees
    3.08
     tree
    2.83
    trees
    2.45
     Trees
    2.44
    tree
    2.44
     Tree
    2.39
    Trees
    2.28
     shrubs
    2.20
    Tree
    2.17
     woody
    2.11
    Activations Density 0.032%

    No Known Activations