© 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. 10-GEMMASCOPE-RES-131K
    7. 43780
    Prev
    Next
    INDEX
    Explanations

    time or quantity remaining

    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
     voleva
    -2.44
     faceva
    -2.38
    要求
    -2.34
     chiede
    -2.33
     beneficiario
    -2.22
    风
    -2.11
    淙
    -2.11
     définiti
    -2.11
    眼睛
    -2.06
    颜色
    -2.03
    POSITIVE LOGITS
    vantaged
    2.95
    ↵
    2.45
     "
    2.23
    their
    2.20
     Not
    2.17
    ization
    2.16
    玙
    2.16
    翾
    2.11
    姈
    2.08
    焌
    2.06
    Activations Density 0.002%

    No Known Activations