© 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. 100249
    Prev
    Next
    INDEX
    Explanations

    worker conditions and activities

    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
    ’
    -3.36
    ↵
    -2.48
    
    -2.38
     '
    -2.25
    轳
    -2.22
    .”
    -2.19
    鈰
    -2.19
    acterísticas
    -2.13
     muut
    -2.06
     policiales
    -2.06
    POSITIVE LOGITS
     Their
    2.53
     Thus
    2.39
    </td>
    2.39
     Accordingly
    2.34
     Consequently
    2.30
    "
    2.30
     If
    2.28
    狆
    2.25
    翾
    2.20
    ization
    2.19
    Activations Density 0.010%

    No Known Activations