© 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. 34-GEMMASCOPE-RES-131K
    7. 92404
    Prev
    Next
    INDEX
    Explanations

    Chad, Niger, Djibouti, Afar

    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
    inigte
    -0.79
    ↣
    -0.76
     Resolución
    -0.72
    alei
    -0.71
     Sonder
    -0.71
    allar
    -0.71
    Setter
    -0.71
     Mandal
    -0.70
    鬢
    -0.69
    钢铁
    -0.69
    POSITIVE LOGITS
     Chad
    1.00
     Maha
    0.90
    Maha
    0.82
     गर
    0.81
    Chad
    0.77
    .}(
    0.75
     словом
    0.73
     Djibouti
    0.73
     César
    0.72
    César
    0.72
    Activations Density 0.021%

    No Known Activations