© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103569
    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
     haces
    -1.13
    unächst
    -1.03
     cristianos
    -0.98
    ライフ
    -0.96
     sacerdotes
    -0.96
     вектор
    -0.96
    Musique
    -0.96
     desnuda
    -0.94
    哪怕
    -0.93
     cristianismo
    -0.93
    POSITIVE LOGITS
    WHEREAS
    0.97
    Ổ
    0.95
     dokładnie
    0.88
     unusually
    0.85
    日付
    0.82
    eon
    0.81
    haga
    0.81
    oust
    0.80
    Business
    0.79
     iniquity
    0.79
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.