© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104196
    Prev
    Next
    INDEX
    Explanations

    justice, courts, judges

    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
     BOTH
    -1.46
     \%$.
    -1.27
    etton
    -1.26
    ucun
    -1.25
     EVERYONE
    -1.23
    茄子
    -1.20
     стало
    -1.19
    RITION
    -1.19
     marshes
    -1.18
     Цена
    -1.18
    POSITIVE LOGITS
     it
    1.61
    ది
    1.32
     try
    1.30
     will
    1.28
    ↵↵
    1.27
     what
    1.22
     they
    1.20
    of
    1.17
    rs
    1.16
    ㈯
    1.13
    Activations Density 0.184%

    No Known Activations