© 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. 2
    Prev
    Next
    INDEX
    Explanations

    code snippets with `require`

    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
     their
    -2.42
     by
    -2.14
     for
    -1.96
     both
    -1.96
     not
    -1.94
     all
    -1.93
     only
    -1.85
     an
    -1.84
     first
    -1.80
     purposefully
    -1.78
    POSITIVE LOGITS
     trám
    1.84
     erhi
    1.81
     weihnachten
    1.77
     パッド
    1.77
    appears
    1.75
     certamente
    1.74
     REALLY
    1.71
    commonly
    1.69
     เมื่อ
    1.66
    なども
    1.66
    Activations Density 0.003%

    No Known Activations