© 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. 10-GEMMASCOPE-RES-131K
    7. 12650
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     também
    -1.04
    ment
    -1.02
    見つ
    -0.94
    const
    -0.94
    month
    -0.91
    lev
    -0.90
     demas
    -0.90
    ஂ
    -0.89
    b
    -0.89
    para
    -0.88
    POSITIVE LOGITS
    НО
    1.02
    FIVE
    0.96
    runOnUiThread
    0.96
    MSRP
    0.95
    conector
    0.92
    guigu
    0.91
    salomon
    0.91
    曖昧さ回避
    0.88
    Doi
    0.88
    鍇
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.