© 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. 81021
    Prev
    Next
    INDEX
    Explanations

    k-fold, k-means, k-th, N-particle, t-SNE

    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
    答え
    -0.80
    bench
    -0.80
    Nonlinear
    -0.79
    ciato
    -0.76
    わずか
    -0.76
    滦
    -0.75
    qian
    -0.73
    觞
    -0.73
    hearsal
    -0.73
    gaming
    -0.73
    POSITIVE LOGITS
    fold
    0.87
    安全性
    0.81
     sided
    0.81
    rmtree
    0.79
     ary
    0.79
     hottest
    0.79
    iramente
    0.77
    th
    0.77
     שב
    0.74
     fold
    0.74
    Activations Density 0.032%

    No Known Activations