© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 127584
    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
     Empfang
    -0.98
     adota
    -0.90
    “
    -0.88
    Kinda
    -0.81
    看出
    -0.80
    .
    -0.80
    𝑎
    -0.80
     könne
    -0.79
    .|
    -0.78
    パッド
    -0.77
    POSITIVE LOGITS
    thmus
    1.14
    騷
    1.07
    鮡
    1.03
    बाइल
    1.02
    agang
    0.96
    壟
    0.96
    ítimo
    0.96
    río
    0.95
    enderung
    0.95
    бираем
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.