© 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. 40009
    Prev
    Next
    INDEX
    Explanations

    fashion industry

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

    The neuron selectively activates on the word “fashion” (in any capitalization or variant) throughout the text.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    蹕
    -3.11
    .";
    -2.80
    荦
    -2.70
     publico
    -2.56
    ⡯
    -2.55
    伱
    -2.52
     abbildung
    -2.42
    ଢ
    -2.42
     cartier
    -2.41
    厯
    -2.41
    POSITIVE LOGITS
    .
    4.63
    ↵
    3.80
    Y
    3.59
    5
    3.25
    </b>
    3.22
    ”
    3.17
    C
    3.05
    g
    2.95
    L
    2.75
    ro
    2.67
    Activations Density 0.007%

    No Known Activations