© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 53996
    Prev
    Next
    INDEX
    Explanations

    Windows Forms applications

    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
    allage
    -1.10
     different
    -1.07
     convierten
    -1.03
     on
    -0.98
     either
    -0.94
     generan
    -0.94
     messaggio
    -0.93
     a
    -0.92
     generó
    -0.91
     our
    -0.91
    POSITIVE LOGITS
    𞤢
    1.30
     contribución
    1.18
    ztes
    1.14
    ocarpus
    1.13
     NEEDED
    1.12
    windows
    1.12
     but
    1.12
    ᷆
    1.10
    腘
    1.10
    Windows
    1.09
    Activations Density 0.019%

    No Known Activations