© 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. 22-GEMMASCOPE-RES-131K
    7. 129459
    Prev
    Next
    INDEX
    Explanations

    people being asked or told things

    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_22/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
     you
    -1.13
    คง
    -1.01
     erscheinen
    -0.99
     was
    -0.95
     now
    -0.95
    你有
    -0.94
    察觉
    -0.93
    暧
    -0.90
     your
    -0.87
    绮
    -0.87
    POSITIVE LOGITS
     usually
    2.27
     suele
    1.92
     often
    1.86
    usually
    1.67
     brukar
    1.61
    Usually
    1.57
     typically
    1.56
     their
    1.56
     Usually
    1.56
     costuma
    1.55
    Activations Density 0.065%

    No Known Activations