© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13981
    Prev
    Next
    INDEX
    Explanations

    swearing and oaths

    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_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
    个月
    -1.97
     και
    -1.87
     heridas
    -1.81
     daño
    -1.76
     dudas
    -1.75
     bebidas
    -1.74
     estrés
    -1.72
     applaud
    -1.72
    簠
    -1.66
     »
    -1.65
    POSITIVE LOGITS
     malat
    1.49
    所
    1.44
     palab
    1.43
     อย่าง
    1.41
     metic
    1.41
     in
    1.40
     comesti
    1.40
    疍
    1.38
     kili
    1.37
     necess
    1.35
    Activations Density 0.007%

    No Known Activations