© 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. 67892
    Prev
    Next
    INDEX
    Explanations

    nanoscale, nanospheres, nanosheets

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

    The neuron detects the prefix "nano" in scientific terminology related to nanoscale structures and materials.

    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
    挲
    -2.63
    鶘
    -2.38
    ↵↵
    -2.36
    当我
    -2.31
    猡
    -2.25
    穑
    -2.22
    ﹍﹍
    -2.13
    0
    -2.11
    Yah
    -2.08
    ,
    -2.03
    POSITIVE LOGITS
    </h3>
    3.05
    KommentareTeilen
    2.89
     Таким
    2.61
     Также
    2.59
    </sub>
    2.45
     Именно
    2.45
     behalf
    2.39
    ！」
    2.39
    uatan
    2.38
    齜
    2.38
    Activations Density 0.056%

    No Known Activations