© 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. 115908
    Prev
    Next
    INDEX
    Explanations

    rates and averages

    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
     revital
    -1.00
     for
    -0.97
     first
    -0.94
     longstanding
    -0.93
     ostensibly
    -0.92
     burgeoning
    -0.92
     in
    -0.91
     extensive
    -0.91
     oddly
    -0.91
     while
    -0.89
    POSITIVE LOGITS
     daily
    1.98
     averages
    1.88
     average
    1.86
    平均
    1.80
    average
    1.76
    每天
    1.74
     averaging
    1.71
    daily
    1.68
    Average
    1.63
    approximately
    1.59
    Activations Density 0.068%

    No Known Activations