© 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. 2317
    Prev
    Next
    INDEX
    Explanations

    folklor, dances, typical Bolivian food or Polish dances

    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
     köp
    -0.89
     تحمل
    -0.84
    Cocina
    -0.83
     اندروید
    -0.83
    ッキリ
    -0.83
     caen
    -0.82
     موبایل
    -0.82
    کنون
    -0.82
     selera
    -0.82
     Cromwell
    -0.81
    POSITIVE LOGITS
     دے
    0.80
    Bai
    0.77
     git
    0.76
    جلس
    0.75
    チャ
    0.75
    酒
    0.74
     folklor
    0.73
    NIST
    0.73
    NFTs
    0.73
     comb
    0.72
    Activations Density 0.024%

    No Known Activations