© 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. 41809
    Prev
    Next
    INDEX
    Explanations

    communion or communication

    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
     französische
    -3.53
    谞
    -3.03
    ↵
    -2.84
    ‪.‬‬
    -2.66
     ehemalige
    -2.59
    
    -2.42
    ぅ
    -2.41
    鏖
    -2.39
    </h3>
    -2.31
    其妙
    -2.31
    POSITIVE LOGITS
    </b>
    3.17
    a
    3.11
     Saltar
    2.69
    %
    2.59
    </sup>
    2.56
    ...
    2.33
     But
    2.31
    ा
    2.30
     "
    2.28
     Now
    2.28
    Activations Density 0.006%

    No Known Activations