© 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. 50245
    Prev
    Next
    INDEX
    Explanations

    a.e. or o.ä

    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
    ଘ
    -0.84
    inam
    -0.82
    lijf
    -0.81
    κι
    -0.77
     MILLION
    -0.75
    essége
    -0.72
    streak
    -0.71
    million
    -0.71
    وها
    -0.71
     مترجم
    -0.69
    POSITIVE LOGITS
     B
    0.93
     Chr
    0.81
    Chr
    0.75
    埗
    0.73
     д
    0.72
    Futures
    0.66
     Hop
    0.65
     št
    0.65
    Choices
    0.64
     zakon
    0.64
    Activations Density 0.044%

    No Known Activations