© 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. 130271
    Prev
    Next
    INDEX
    Explanations

    Markdown structure and code comments

    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
     These
    -1.39
     So
    -1.38
     You
    -1.38
     They
    -1.36
     This
    -1.31
     It
    -1.31
     Therefore
    -1.31
     My
    -1.29
     The
    -1.28
     "
    -1.25
    POSITIVE LOGITS
    蕯
    1.45
     döner
    1.41
    ↵
    1.40
    Rumah
    1.38
    tså
    1.34
    Zutaten
    1.30
    我們
    1.27
    Подробнее
    1.25
    鐽
    1.24
    鼕
    1.22
    Activations Density 0.002%

    No Known Activations