© 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. 101170
    Prev
    Next
    INDEX
    Explanations

    favor and related concepts

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

    The neuron is triggered by occurrences of the word “favor” (including its British spelling “favour” and plural forms) in the text.

    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
     proprietario
    -1.64
    .}(
    -1.52
     onderdelen
    -1.43
     welchem
    -1.37
     only
    -1.37
    in
    -1.32
     entregó
    -1.30
     tendenza
    -1.27
     fijar
    -1.27
     demselben
    -1.27
    POSITIVE LOGITS
    sieurs
    1.55
     Cbd
    1.55
     speciale
    1.51
    饧
    1.50
     ….
    1.49
    躄
    1.47
    ピアス
    1.46
     comprende
    1.40
     nachdem
    1.36
    大于
    1.36
    Activations Density 0.014%

    No Known Activations