© 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. 42194
    Prev
    Next
    INDEX
    Explanations

    US government agencies

    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
    améli
    -1.91
    gherita
    -1.87
     However
    -1.86
    ITERIA
    -1.81
    itempty
    -1.80
    苙
    -1.78
    GraphicsUnit
    -1.78
     bustling
    -1.76
    (")");
    -1.75
    fallout
    -1.74
    POSITIVE LOGITS
    ↵↵
    2.22
     and
    2.17
     "
    1.82
    wwwww
    1.58
    men
    1.58
     Octobre
    1.57
     departement
    1.52
     certificat
    1.50
    the
    1.46
    in
    1.45
    Activations Density 0.052%

    No Known Activations