© 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. 26687
    Prev
    Next
    INDEX
    Explanations

    official announcements and greetings

    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
     chré
    -2.02
     religieux
    -1.72
     chrétien
    -1.56
     religieuses
    -1.49
    ׇ
    -1.47
    ֩
    -1.45
     eccl
    -1.38
     didn
    -1.36
    𝐊
    -1.36
     メニュー
    -1.33
    POSITIVE LOGITS
     our
    2.28
    ּוֹ
    1.70
    Our
    1.64
     Our
    1.50
     ourselves
    1.45
    Similarly
    1.41
     we
    1.38
     μας
    1.33
    そのような
    1.32
     będziemy
    1.32
    Activations Density 0.015%

    No Known Activations