© 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. 12771
    Prev
    Next
    INDEX
    Explanations

    C++ std library

    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
    </h3>
    -2.17
    鹋
    -2.16
    ysteem
    -2.03
    <bos>
    -1.99
     lesquels
    -1.94
    だけです
    -1.90
    羕
    -1.89
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.89
    </i>
    -1.88
     defunct
    -1.87
    POSITIVE LOGITS
    .,
    2.80
    \
    2.58
    ،
    2.16
    *
    2.14
     informací
    2.03
    ;,
    2.02
    战胜
    2.02
    
    2.00
     小学生
    1.98
    ',
    1.95
    Activations Density 0.010%

    No Known Activations