© 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. 112639
    Prev
    Next
    INDEX
    Explanations

    no exception or different

    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
     then
    -1.55
     you
    -1.47
     using
    -1.28
    ficamente
    -1.27
     because
    -1.25
    escalier
    -1.23
     its
    -1.23
     тогда
    -1.20
    because
    -1.17
     and
    -1.16
    POSITIVE LOGITS
    こともあり
    1.44
     každé
    1.28
    何度も
    1.27
     chaque
    1.26
    朋友圈
    1.23
    illeurs
    1.21
    ことがあります
    1.17
    取决
    1.17
     among
    1.16
    lanze
    1.16
    Activations Density 0.024%

    No Known Activations