© 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. 39891
    Prev
    Next
    INDEX
    Explanations

    disposal of waste or products

    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
    苳
    -2.61
    在自己
    -2.53
     conforto
    -2.47
     experiences
    -2.45
    ate
    -2.39
     aparecen
    -2.33
     сотрудники
    -2.33
    轳
    -2.31
    跩
    -2.31
    らは
    -2.31
    POSITIVE LOGITS
    </strong>
    2.97
    
    2.89
    ↵
    2.88
    鳢
    2.59
    zehnten
    2.50
    ";
    2.47
     сист
    2.36
    逦
    2.36
    a
    2.36
    熜
    2.33
    Activations Density 0.005%

    No Known Activations