© 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. 34-GEMMASCOPE-RES-131K
    7. 30663
    Prev
    Next
    INDEX
    Explanations

    tradespeople services and registration

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

    The neuron is triggered by long sequences of uppercase text—e.g. headings, menu labels, or other all-caps words.

    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
     refinancing
    -0.81
     dredge
    -0.74
     Yay
    -0.73
     urządzenia
    -0.73
    cipitation
    -0.73
     Towne
    -0.72
     municipale
    -0.71
    𝘯
    -0.71
     Escrow
    -0.71
    ubert
    -0.71
    POSITIVE LOGITS
     trades
    1.33
     tiling
    1.01
    trade
    1.00
     trade
    0.98
     reformas
    0.94
     plaster
    0.94
     cowboy
    0.92
     traders
    0.92
     TRADE
    0.92
     damp
    0.91
    Activations Density 0.018%

    No Known Activations