© 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. 59019
    Prev
    Next
    INDEX
    Explanations

    ferromanganese, monolith, base metals, compression fossil, dating, wind direction, flat to, jarosite

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

    geological and mineralogical terms related to earth science.

    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
     ہے۔
    -0.95
    dedu
    -0.92
     teren
    -0.88
     Keuangan
    -0.85
    你们的
    -0.85
    機種
    -0.84
     美丽
    -0.83
    
    -0.81
    私には
    -0.81
     pleasantly
    -0.81
    POSITIVE LOGITS
     facies
    1.03
     dingen
    0.98
    NJ
    0.90
    ,\,\
    0.85
    认识
    0.85
    urangi
    0.83
     orsz
    0.79
    JV
    0.79
     aquel
    0.78
    IAB
    0.78
    Activations Density 0.033%

    No Known Activations