© 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. 34-GEMMASCOPE-RES-131K
    7. 48238
    Prev
    Next
    INDEX
    Explanations

    shirts and suits

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

    The neuron strongly activates on text that looks like section titles, headlines, or other high-level formatting markers (e.g. document headings and separator lines).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Jad
    -0.72
     hairpin
    -0.71
     gardening
    -0.70
    letar
    -0.69
     tapestry
    -0.68
    peth
    -0.68
     Marit
    -0.66
    끈
    -0.66
     ORF
    -0.66
     Cookbook
    -0.65
    POSITIVE LOGITS
     shirt
    1.89
     shirts
    1.67
     Shirt
    1.57
    Shirt
    1.42
    shirts
    1.34
    shirt
    1.30
     Shirts
    1.24
     camisa
    1.19
    Shirts
    1.17
     suit
    1.13
    Activations Density 0.036%

    No Known Activations