© 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. 110681
    Prev
    Next
    INDEX
    Explanations

    forests and woodlands

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

    descriptions of ecological habitats, particularly forests, wetlands, and natural environments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    érape
    -0.80
     アウト
    -0.77
     userManager
    -0.76
     sustainability
    -0.73
     lembrar
    -0.73
    ureux
    -0.73
     Balla
    -0.73
    gendes
    -0.72
    thenReturn
    -0.70
     LANDSCAPE
    -0.70
    POSITIVE LOGITS
     mixed
    1.17
     scrub
    1.08
     grassland
    0.93
     transitional
    0.92
    Mixed
    0.91
     dominated
    0.91
     dry
    0.89
     Mixed
    0.88
    ransition
    0.88
     transición
    0.87
    Activations Density 0.036%

    No Known Activations