© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84242
    Prev
    Next
    INDEX
    Explanations

    RabbitMQ and related compounds

    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
    ཫ
    -3.28
    
    -3.19
    𐐀
    -2.97
    
    -2.75
    ྕ
    -2.75
     katk
    -2.61
    苼
    -2.58
    퐿
    -2.56
    lük
    -2.47
    乆
    -2.45
    POSITIVE LOGITS
    </h1>
    3.67
    </i>
    3.64
    <i>
    3.38
    ");
    3.13
    </td>
    2.81
    the
    2.70
    );
    2.64
     When
    2.55
    </b>
    2.53
    section
    2.53
    Activations Density 0.008%

    No Known Activations