© 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. 72930
    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
    uyện
    -1.08
    atiana
    -1.02
    gbar
    -1.02
    yym
    -1.00
    favourable
    -0.96
    utilise
    -0.96
     gillar
    -0.95
     boasting
    -0.92
     depict
    -0.91
     promotes
    -0.91
    POSITIVE LOGITS
     disponibili
    1.01
    虧
    0.94
    MEDI
    0.90
    queness
    0.90
     مثال
    0.90
    medi
    0.90
     например
    0.86
    ⽼
    0.84
    barer
    0.84
    staging
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.