© 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. 42016
    Prev
    Next
    INDEX
    Explanations

    code comment copyright license

    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
    <td>
    -2.33
    ſelves
    -2.23
     disciplinas
    -2.05
    焄
    -1.98
    閹
    -1.98
     When
    -1.96
    九年
    -1.94
     ошибка
    -1.91
    LEZ
    -1.91
     ſou
    -1.91
    POSITIVE LOGITS
    te
    2.86
    ti
    2.48
    ING
    2.28
    m
    2.27
    /"
    2.20
    ’
    2.20
    ']>
    2.19
    le
    2.17
     worin
    2.17
    to
    2.14
    Activations Density 0.003%

    No Known Activations