© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 104258
    Prev
    Next
    INDEX
    Explanations

    clothing and accessories

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

    The neuron fires on standalone nouns naming tangible objects—especially articles of clothing and similar personal items.

    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
    </b>
    -1.66
    うちの
    -1.45
    </strong>
    -1.38
     '
    -1.37
     but
    -1.33
     amalgam
    -1.28
    ncia
    -1.23
    -'
    -1.22
     berbagai
    -1.21
    s
    -1.21
    POSITIVE LOGITS
    They
    1.63
    There
    1.48
    These
    1.47
    You
    1.43
    ]
    1.41
    If
    1.41
    
    1.38
    We
    1.37
    ссор
    1.33
     producenta
    1.31
    Activations Density 0.045%

    No Known Activations