© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14013
    Prev
    Next
    INDEX
    Explanations

    Both main or incidence of

    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
     τους
    -1.04
     TÉCNICA
    -1.02
     PUEDE
    -0.98
     mereka
    -0.95
     niyang
    -0.94
     deceiving
    -0.91
    ῳ
    -0.89
    furter
    -0.87
     لهم
    -0.86
    мога
    -0.85
    POSITIVE LOGITS
     приходится
    0.97
     zamiast
    0.96
    oliber
    0.93
    ცი
    0.91
    ໂ
    0.90
    uper
    0.87
     is
    0.87
     właśnie
    0.84
     съм
    0.84
     noastră
    0.83
    Activations Density 0.000%

    No Known Activations