© 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. 128651
    Prev
    Next
    INDEX
    Explanations

    hands-on practice and experience

    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
    ｾ
    -0.90
     altri
    -0.83
     informazioni
    -0.82
    options
    -0.81
    簡単に
    -0.78
     narration
    -0.77
     information
    -0.77
     intelligence
    -0.76
     köp
    -0.76
    forChild
    -0.75
    POSITIVE LOGITS
     test
    1.59
    実
    1.27
     tests
    1.24
    実際に
    1.22
     practical
    1.20
     practice
    1.10
     testing
    1.09
    jsxFileName
    1.08
     реаль
    1.07
    测试
    1.06
    Activations Density 0.088%

    No Known Activations