© 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. 22-GEMMASCOPE-RES-131K
    7. 35565
    Prev
    Next
    INDEX
    Explanations

    Abercrombie & Fitch

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

    The neuron strongly activates on the uppercase article “The” when it appears as part of site navigation or book‐title headings.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     two
    -1.26
     three
    -1.23
     at
    -1.22
     his
    -1.20
     both
    -1.18
     several
    -1.05
     their
    -1.02
     all
    -1.00
     six
    -0.94
     operational
    -0.92
    POSITIVE LOGITS
    ugin
    1.30
    関連リンク
    1.15
    ぽん
    1.15
    
    1.13
    
    1.09
    あぁ
    1.09
    ഛ
    1.08
     promesse
    1.07
    達の
    1.05
    に似
    1.05
    Activations Density 0.036%

    No Known Activations