© 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. 102983
    Prev
    Next
    INDEX
    Explanations

    roles and contributions

    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
     maksimum
    -1.50
     its
    -1.49
     rusa
    -1.45
     susun
    -1.41
     andererseits
    -1.36
     folgendes
    -1.35
     Francus
    -1.34
     behaupten
    -1.33
     \\
    -1.30
    bró
    -1.27
    POSITIVE LOGITS
     zusammen
    1.46
    ap
    1.36
    に出演
    1.34
     berperan
    1.32
    ktionen
    1.28
    ay
    1.25
     الإن
    1.20
    攆
    1.18
    ropshire
    1.17
     here
    1.16
    Activations Density 0.043%

    No Known Activations