© 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. 82891
    Prev
    Next
    INDEX
    Explanations

    ancient Iranian religions

    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
     мульт
    -0.79
    繚
    -0.77
     Scot
    -0.73
    umes
    -0.73
    Sierra
    -0.73
     Bracken
    -0.72
    MySQL
    -0.72
    nija
    -0.71
    KeySpec
    -0.69
     divergence
    -0.68
    POSITIVE LOGITS
     Zoro
    2.25
    Zoro
    1.59
     Mazda
    1.24
     Mani
    1.18
     dual
    1.16
     fire
    1.12
    dual
    1.11
    Dual
    1.09
     Dual
    1.09
     Iranian
    1.07
    Activations Density 0.040%

    No Known Activations