© 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. 10-GEMMASCOPE-RES-131K
    7. 21000
    Prev
    Next
    INDEX
    Explanations

    system includes and module names

    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_10/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
    ！"
    -1.71
    。"
    -1.59
     misguided
    -1.55
     debilitating
    -1.52
    fristi
    -1.50
    γραφή
    -1.49
     intricate
    -1.48
     ONLY
    -1.44
     striving
    -1.43
     duas
    -1.41
    POSITIVE LOGITS
     that
    1.67
    糴
    1.54
     the
    1.49
     wasn
    1.39
    .
    1.37
    possibly
    1.36
     was
    1.36
     crucial
    1.35
     to
    1.34
     REALLY
    1.34
    Activations Density 0.000%

    No Known Activations