© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85635
    Prev
    Next
    INDEX
    Explanations

    runway, catwalk, carpet, shows

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

    The neuron flags words that name or describe fashion runways or shows (e.g., runway, catwalk, fashion show, couture show).

    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
    “,
    -2.02
    ),
    -1.94
    ”,
    -1.87
    “
    -1.84
    )
    -1.66
     Additionally
    -1.65
    !”
    -1.59
     is
    -1.50
     aktuellen
    -1.49
     Also
    -1.48
    POSITIVE LOGITS
     kreuz
    1.54
     raconte
    1.41
    絎
    1.36
     spada
    1.33
    showed
    1.33
    ༷
    1.32
    ⢇
    1.32
    laboratory
    1.30
    ;"
    1.29
     Niveau
    1.28
    Activations Density 0.011%

    No Known Activations