© 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. 65410
    Prev
    Next
    INDEX
    Explanations

    historic and cultural resources

    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
     Tweet
    -0.76
     dific
    -0.76
     accesible
    -0.69
    檸
    -0.69
    Playlist
    -0.69
     Geology
    -0.68
    isuke
    -0.68
    utrients
    -0.68
    τών
    -0.68
    ьера
    -0.67
    POSITIVE LOGITS
     cultural
    1.01
    Consulting
    0.98
    Cultural
    0.94
    cultural
    0.93
     consulting
    0.92
    Historic
    0.90
     التاريخ
    0.89
    archae
    0.88
     archaeologists
    0.88
     historic
    0.88
    Activations Density 0.016%

    No Known Activations