© 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. 130211
    Prev
    Next
    INDEX
    Explanations

    favorable outcomes

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

    The neuron picks out occurrences of the adjective “favorable” (including its British spelling “favourable”).

    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
     dritte
    -2.84
     komplette
    -2.63
    llavero
    -2.56
    két
    -2.56
    鹛
    -2.52
    鬭
    -2.50
    我又
    -2.48
    archiwizowane
    -2.47
    ÁCT
    -2.45
    纐
    -2.45
    POSITIVE LOGITS
    0
    3.70
    呖
    3.19
    .
    3.16
    7
    3.03
    Only
    2.92
    That
    2.91
    their
    2.75
    Through
    2.69
    出て
    2.67
    緜
    2.67
    Activations Density 0.005%

    No Known Activations