© 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. 83710
    Prev
    Next
    INDEX
    Explanations

    positive appraisal and superlatives

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

    The neuron detects noun phrases expressing popularity or acclaim (e.g. “the toast of…,” “crowd favorite,” “politicians’ favorite constituencies”).

    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
     明治
    -0.78
    錳
    -0.70
     vänt
    -0.69
     записа
    -0.68
     réel
    -0.67
    ご購入
    -0.66
    COLON
    -0.65
    Laughter
    -0.65
    вра
    -0.63
    uera
    -0.63
    POSITIVE LOGITS
     darling
    3.80
     dar
    2.72
     Darling
    2.42
    Darling
    2.42
    dar
    2.30
     favorite
    1.94
     favourite
    1.76
     golden
    1.73
     sweetheart
    1.71
    宠
    1.71
    Activations Density 0.066%

    No Known Activations