© 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. 85342
    Prev
    Next
    INDEX
    Explanations

    designs and patterns

    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
    \
    -1.77
    with
    -1.52
    2
    -1.46
    N
    -1.43
    8
    -1.41
    for
    -1.28
    0
    -1.27
    也有
    -1.24
     imágen
    -1.24
    ที่ดี
    -1.23
    POSITIVE LOGITS
     emballage
    1.45
    嵎
    1.38
    鑷
    1.38
    nivea
    1.37
     appareil
    1.34
    tigte
    1.34
    tinta
    1.33
    tivamente
    1.33
    ⁎
    1.32
    jourd
    1.30
    Activations Density 0.057%

    No Known Activations