© 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. 10-GEMMASCOPE-RES-131K
    7. 75174
    Prev
    Next
    INDEX
    Explanations

    human brain, eye, operator

    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
     for
    -1.79
    楢
    -1.23
     you
    -1.22
     onderstaande
    -1.14
     metav
    -1.13
    高达
    -1.11
     suivantes
    -1.11
     unknownFields
    -1.10
    报告
    -1.09
    栃
    -1.09
    POSITIVE LOGITS
     will
    1.41
     поколения
    1.34
    with
    1.33
     требуется
    1.33
    させて頂きます
    1.30
    》（
    1.28
     only
    1.27
    打开了
    1.27
     venit
    1.27
     who
    1.26
    Activations Density 0.046%

    No Known Activations