© 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. 81433
    Prev
    Next
    INDEX
    Explanations

    Lincoln + specific places and people

    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
    েই
    -0.89
     been
    -0.87
    凌晨
    -0.79
    ってみる
    -0.79
    Converted
    -0.79
    麈
    -0.79
     feita
    -0.78
    NetCore
    -0.78
     actualidad
    -0.77
    상
    -0.77
    POSITIVE LOGITS
     Logs
    1.23
     logs
    1.09
    Logs
    0.93
     penny
    0.87
     Log
    0.86
    ιλ
    0.86
     contributor
    0.82
    łowa
    0.82
    писок
    0.81
     Mercury
    0.80
    Activations Density 0.012%

    No Known Activations