© 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. 72104
    Prev
    Next
    INDEX
    Explanations

    questions and introductions

    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
     “
    -1.52
     Covid
    -1.32
    <strong>
    -1.23
     COVID
    -1.21
     ‘
    -1.21
     „
    -1.17
    “
    -1.14
     covid
    -1.14
     U
    -1.13
    !
    -1.13
    POSITIVE LOGITS
     something
    1.43
     rajut
    1.38
     图库
    1.30
     läßt
    1.29
     procesu
    1.28
     certain
    1.28
    ⼿
    1.27
    atification
    1.25
     gewiß
    1.23
     ۱۳۸
    1.21
    Activations Density 0.011%

    No Known Activations