© 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. 3729
    Prev
    Next
    INDEX
    Explanations

    ensuited bathrooms, adjoining rooms

    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>
    -2.52
     It
    -2.06
     If
    -1.95
    </em>
    -1.91
    );
    -1.80
     be
    -1.77
    </h2>
    -1.72
    蛩
    -1.66
    '];
    -1.64
    %);
    -1.61
    POSITIVE LOGITS
    這個
    1.75
    ⣉
    1.75
    澌
    1.67
     and
    1.66
    
    1.59
    НЫЕ
    1.52
    飧
    1.52
     katk
    1.51
     acuario
    1.51
     Opiniones
    1.50
    Activations Density 0.004%

    No Known Activations