© 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. 72638
    Prev
    Next
    INDEX
    Explanations

    extramarital affairs, extracurricular activities

    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
     یا
    -2.52
     или
    -2.22
     It
    -2.06
     したい
    -1.94
    或
    -1.91
    Perhaps
    -1.84
    目前的
    -1.82
    Some
    -1.78
     With
    -1.74
    heureusement
    -1.69
    POSITIVE LOGITS
     hohem
    2.05
     hoher
    2.02
     aad
    1.99
     cerámica
    1.98
     wszystkim
    1.93
     großem
    1.93
     arid
    1.91
    mlı
    1.88
     extracurricular
    1.85
    کننده
    1.84
    Activations Density 0.001%

    No Known Activations