© 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. 11909
    Prev
    Next
    INDEX
    Explanations

    compliance with licenses

    np_acts-logits-general · gemini-2.5-flash-lite

    phrases in legal/technical contexts indicating requirements or conditions, particularly "compliance," "already know," "close/based on," and "enabled."

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     любой
    -1.49
    廰
    -1.41
    atiana
    -1.39
    ",
    -1.37
    ̣c
    -1.33
    ̀ng
    -1.32
     ザ
    -1.31
    ’,
    -1.30
     และ
    -1.27
    
    -1.27
    POSITIVE LOGITS
     as
    2.58
     by
    2.55
     through
    2.36
     for
    1.98
     from
    1.77
     it
    1.77
     via
    1.68
     in
    1.56
     if
    1.55
     one
    1.52
    Activations Density 0.183%

    No Known Activations