© 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. 34-GEMMASCOPE-RES-131K
    7. 38044
    Prev
    Next
    INDEX
    Explanations

    dates and measurements

    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_34/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
     vlast
    -0.77
     below
    -0.76
    ickory
    -0.75
    neighborhood
    -0.74
    otts
    -0.73
    ern
    -0.73
     świąte
    -0.71
    🚮
    -0.71
     Medizin
    -0.71
    に行ってきました
    -0.71
    POSITIVE LOGITS
    ></
    0.88
     WES
    0.78
    TR
    0.78
    ,</
    0.77
    ulence
    0.77
    </
    0.77
    でお
    0.71
     loadData
    0.71
     ร
    0.70
    Rachel
    0.70
    Activations Density 0.000%

    No Known Activations