© 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. 98528
    Prev
    Next
    INDEX
    Explanations

    bullying

    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
    Bem
    -0.80
     COMPAR
    -0.80
    冲击
    -0.79
     scandalous
    -0.78
    Consumo
    -0.76
     abstrato
    -0.75
    нео
    -0.74
    utable
    -0.73
     הרי
    -0.73
    FORMAN
    -0.72
    POSITIVE LOGITS
     bullying
    3.86
     bully
    3.52
     bullied
    3.14
     bullies
    3.13
     Bullying
    2.80
    bullying
    2.78
     Bully
    2.45
     BULL
    2.16
    Bull
    2.14
    Bul
    1.88
    Activations Density 0.037%

    No Known Activations