© 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. 65617
    Prev
    Next
    INDEX
    Explanations

    rude or negative staff attitudes

    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
    啐
    -1.09
     forgiving
    -0.97
     brukar
    -0.96
    inkler
    -0.94
     pantalón
    -0.93
    拍了拍
    -0.91
     sane
    -0.88
    ciful
    -0.86
    caping
    -0.86
     praises
    -0.86
    POSITIVE LOGITS
     attitude
    1.80
    attitude
    1.51
     attitudes
    1.32
     Attitude
    1.27
     rude
    1.23
    rude
    1.21
    Attitude
    1.18
     Rude
    1.16
     actitud
    1.16
     rud
    1.15
    Activations Density 0.009%

    No Known Activations