© 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. 13998
    Prev
    Next
    INDEX
    Explanations

    bag or bags

    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
    ↵↵
    -2.23
    from
    -2.17
    or
    -2.02
    G
    -1.99
     -
    -1.98
     —
    -1.91
    re
    -1.90
    .
    -1.87
     )
    -1.79
    *
    -1.74
    POSITIVE LOGITS
     bags
    2.31
    genodigd
    2.22
    testen
    2.11
    虯
    2.02
     bolsa
    2.00
     Bags
    1.95
    修士
    1.93
     otras
    1.93
    鼇
    1.92
    dags
    1.90
    Activations Density 0.016%

    No Known Activations