© 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. 58630
    Prev
    Next
    INDEX
    Explanations

    kind or type of

    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
    ⾔
    -1.97
    guigu
    -1.72
     '',
    -1.64
     allerlei
    -1.62
     合集
    -1.60
     ビキニ
    -1.56
    "",
    -1.54
    ıy
    -1.51
     フリル
    -1.47
    kleid
    -1.46
    POSITIVE LOGITS
     of
    2.75
     we
    1.96
     if
    1.91
     should
    1.89
     people
    1.87
     thing
    1.80
     nossas
    1.77
     can
    1.75
     time
    1.73
     result
    1.73
    Activations Density 0.008%

    No Known Activations