© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4251
    Prev
    Next
    INDEX
    Explanations

    US states and cities

    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_34/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
     Turin
    -0.73
    ⟭
    -0.71
    늘
    -0.71
     Spokane
    -0.70
     Gelen
    -0.70
    quia
    -0.69
     Infer
    -0.69
     தே
    -0.67
    Ƽ
    -0.66
     Gauthier
    -0.66
    POSITIVE LOGITS
     Mank
    1.14
    نز
    0.86
    colorbar
    0.82
    coloured
    0.80
     sako
    0.79
    ၆
    0.77
     Wiltshire
    0.75
     LinkedIn
    0.75
     Mortuary
    0.75
    colored
    0.75
    Activations Density 0.010%

    No Known Activations