© 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. 119468
    Prev
    Next
    INDEX
    Explanations

    Cyrillic letters, names, dates

    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
    </em>
    -3.09
    ↵
    -2.81
     It
    -2.75
    ↵↵
    -2.61
    l
    -2.55
     Only
    -2.48
    u
    -2.47
     */
    -2.41
    for
    -2.39
     για
    -2.38
    POSITIVE LOGITS
    ’
    3.25
    阏
    2.83
    毟
    2.81
    蓐
    2.69
     afbeeldingen
    2.67
     vijf
    2.64
     afbeelding
    2.64
    嫑
    2.59
    蟊
    2.55
    蜴
    2.52
    Activations Density 0.001%

    No Known Activations