© 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. 43097
    Prev
    Next
    INDEX
    Explanations

    staff services

    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
    頎
    -1.52
     in
    -1.38
    дают
    -1.36
    푡
    -1.30
    ↵
    -1.29
    ходов
    -1.28
    dė
    -1.27
     также
    -1.27
     About
    -1.26
    Then
    -1.23
    POSITIVE LOGITS
     is
    2.59
     who
    1.84
     aquella
    1.70
     trusty
    1.54
    Según
    1.52
    ſſen
    1.40
    only
    1.40
    aş
    1.39
     Deut
    1.38
    MAXN
    1.38
    Activations Density 0.014%

    No Known Activations