© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 98750
    Prev
    Next
    INDEX
    Explanations

    desert locations

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

    desert and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ferries
    0.55
    森林
    0.54
     Pologne
    0.52
     समुद्री
    0.50
    🛥
    0.49
    ătate
    0.48
    ামত
    0.48
    青森
    0.48
    莼
    0.48
     hutan
    0.48
    POSITIVE LOGITS
     Desert
    1.60
     desert
    1.56
    Desert
    1.53
     Arizona
    1.47
    沙漠
    1.47
    Arizona
    1.46
    desert
    1.45
    🏜
    1.38
     Tucson
    1.35
     Mojave
    1.35
    Activations Density 0.420%

    No Known Activations