© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13222
    Prev
    Next
    INDEX
    Explanations

    international organizations and 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
     was
    -2.11
    鹩
    -2.03
    这一幕
    -1.94
    鸸
    -1.90
     ordina
    -1.88
     uſed
    -1.88
    芘
    -1.88
    紲
    -1.88
    遹
    -1.86
     psychiat
    -1.80
    POSITIVE LOGITS
    ю
    1.95
    opardy
    1.89
    
    1.80
     expel
    1.75
    as
    1.73
    en
    1.72
     denying
    1.70
    ن
    1.70
     mundiales
    1.69
     Took
    1.66
    Activations Density 0.003%

    No Known Activations