© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 955
    Prev
    Next
    INDEX
    Explanations

    general descriptor

    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
    )
    -1.67
     That
    -1.59
     to
    -1.50
     These
    -1.42
     Cuando
    -1.41
     For
    -1.37
     allerdings
    -1.35
    HEAST
    -1.34
     When
    -1.32
     Национальный
    -1.32
    POSITIVE LOGITS
     Toute
    1.65
    />";
    1.57
    」,
    1.48
    ."*
    1.48
    錵
    1.45
    _
    1.42
    !”
    1.42
     целом
    1.40
    U
    1.40
     نیز
    1.38
    Activations Density 0.030%

    No Known Activations