© 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. 72874
    Prev
    Next
    INDEX
    Explanations

    code and non-English text

    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
    red
    -1.58
     "
    -1.56
    跸
    -1.42
    _
    -1.38
     dunque
    -1.36
    ate
    -1.34
     производства
    -1.28
     therefore
    -1.27
    了不少
    -1.25
    AtIndexPath
    -1.21
    POSITIVE LOGITS
     that
    1.76
    楽しめます
    1.55
     शुर
    1.50
    驁
    1.45
    𐐪
    1.44
     аккура
    1.43
    덫
    1.35
    gangss
    1.34
    Teatro
    1.33
     ہم
    1.30
    Activations Density 0.000%

    No Known Activations