© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30574
    Prev
    Next
    INDEX
    Explanations

    desert locations and flora

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

    descriptions of desert or arid environments and their associated plants, animals, and geological features.

    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
     forest
    -1.21
    forest
    -1.19
    Forest
    -1.17
     woods
    -1.14
     леса
    -1.11
    woods
    -1.09
     FOREST
    -1.05
     forested
    -1.01
     Forest
    -0.96
    森林
    -0.96
    POSITIVE LOGITS
     desert
    2.72
    desert
    2.47
     Desert
    2.41
    Desert
    2.30
     cactus
    1.91
    cactus
    1.89
     Cactus
    1.84
    沙漠
    1.79
     الصح
    1.78
     пусты
    1.73
    Activations Density 0.096%

    No Known Activations