© 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. 971
    Prev
    Next
    INDEX
    Explanations

    encoding data and strings

    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
    姈
    -3.08
    ᠂
    -2.98
    s
    -2.91
    
    -2.61
    蠵
    -2.47
    ized
    -2.45
    艄
    -2.36
    ’
    -2.28
    های
    -2.27
    🧌
    -2.27
    POSITIVE LOGITS
     Some
    2.75
     BOTH
    2.63
    ↵
    2.53
     NEED
    2.47
     dasarnya
    2.30
     Although
    2.23
     Since
    2.17
     There
    2.17
     не
    2.16
     When
    2.14
    Activations Density 0.004%

    No Known Activations