© 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. 118553
    Prev
    Next
    INDEX
    Explanations

    expressing agreement or disagreement

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    тія
    -0.82
    同様に
    -0.78
     Grammar
    -0.74
    Contrast
    -0.73
    henden
    -0.72
     инфек
    -0.72
     {*}
    -0.71
     friendships
    -0.70
     función
    -0.70
    Corn
    -0.69
    POSITIVE LOGITS
     agree
    2.30
     agrees
    1.73
     agreed
    1.70
     agreement
    1.49
    agree
    1.46
     wholeheartedly
    1.45
     согла
    1.31
     Agree
    1.31
    Agree
    1.27
     agreeing
    1.25
    Activations Density 0.033%

    No Known Activations