© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129848
    Prev
    Next
    INDEX
    Explanations

    introducing further information

    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
    蕷
    -2.72
     we
    -2.39
    ࿙
    -2.38
    猻
    -2.34
     され
    -2.23
    h
    -2.23
    ünster
    -2.22
     has
    -2.17
    鸰
    -2.17
    ꜆
    -2.11
    POSITIVE LOGITS
    酲
    3.27
    .
    3.00
    稣
    2.78
    脔
    2.73
    驁
    2.63
    <em>
    2.59
     内衣
    2.48
     花朵
    2.48
     唯美
    2.47
    淠
    2.47
    Activations Density 0.006%

    No Known Activations