© 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. 59955
    Prev
    Next
    INDEX
    Explanations

    Nord, Ford, or Jord names

    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
    沛
    -0.90
    fileupload
    -0.75
    sites
    -0.72
    lusst
    -0.71
     serangga
    -0.69
    rmi
    -0.68
     המצ
    -0.68
    HANGUL
    -0.68
     vždy
    -0.66
     greatly
    -0.66
    POSITIVE LOGITS
    yce
    1.11
    ama
    0.77
    y
    0.75
    ache
    0.73
    Ո
    0.71
     peu
    0.71
    ajn
    0.70
    ained
    0.70
    lè
    0.69
     bross
    0.69
    Activations Density 0.034%

    No Known Activations