© 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. 23941
    Prev
    Next
    INDEX
    Explanations

    code syntax and identifiers

    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
    </b>
    -2.48
     також
    -2.08
    </h4>
    -1.98
     auch
    -1.92
    ۹
    -1.90
     גם
    -1.88
    也
    -1.81
    ୩
    -1.80
     Other
    -1.77
     zeal
    -1.76
    POSITIVE LOGITS
     „
    2.16
     \"
    2.08
    \
    1.95
    </h3>
    1.92
    啬
    1.90
    ."));
    1.89
    "
    1.77
    „
    1.76
     groei
    1.74
    ;
    1.69
    Activations Density 0.047%

    No Known Activations