© 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. 10-GEMMASCOPE-RES-131K
    7. 39942
    Prev
    Next
    INDEX
    Explanations

    hot springs and baths

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

    locations with natural hot springs or thermal baths.

    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_10/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
    {
    -2.03
     hany
    -1.91
    赑
    -1.86
    釭
    -1.81
    the
    -1.77
     kuna
    -1.71
     ensured
    -1.69
    も行
    -1.66
     the
    -1.63
    
    -1.58
    POSITIVE LOGITS
     increíble
    1.88
     sassy
    1.82
    ㌧
    1.77
     roomy
    1.73
     escala
    1.65
     snowy
    1.63
     bumpy
    1.62
     for
    1.62
    o
    1.59
     wading
    1.58
    Activations Density 0.011%

    No Known Activations