© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83820
    Prev
    Next
    INDEX
    Explanations

    clothing skirts

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

    The neuron primarily detects mentions of “skirt” (including variants like “miniskirt” or plural “skirts”) in the text.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
    Negative Logits
     –
    -2.80
    ཫ
    -2.63
    敺
    -2.59
    ↵
    -2.52
    呖
    -2.34
    ～～～～
    -2.31
    をご紹介します
    -2.28
    期間限定
    -2.27
    在其
    -2.27
     multitude
    -2.27
    POSITIVE LOGITS
    ";
    2.52
    啬
    2.42
    是非常
    2.33
    鉆
    2.33
     celebrated
    2.30
    '
    2.30
     You
    2.23
    珵
    2.13
    是很
    2.13
    archiwizowane
    2.11
    Activations Density 0.003%

    No Known Activations