© 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. 58959
    Prev
    Next
    INDEX
    Explanations

    earth elements or fossils

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

    scientific terminology related to geology, minerals, and 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_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
     then
    -1.35
     الجهاز
    -1.29
    ónia
    -1.24
    ㌘
    -1.23
     anybody
    -1.22
    欧盟
    -1.21
     компьютера
    -1.20
    出了一
    -1.19
     úgy
    -1.18
    дарь
    -1.18
    POSITIVE LOGITS
    ഃ
    1.37
     rozmiar
    1.31
     muñecas
    1.30
    这些
    1.26
    These
    1.23
    Mutagenicity
    1.23
     These
    1.20
    chede
    1.17
    終於
    1.17
     แท้
    1.16
    Activations Density 0.143%

    No Known Activations