© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 42833
    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
    对方的
    -0.89
    Both
    -0.89
     espé
    -0.88
     válvula
    -0.84
    Fiat
    -0.84
     bacté
    -0.84
    Sebagai
    -0.82
    Creating
    -0.81
     both
    -0.81
     saj
    -0.80
    POSITIVE LOGITS
     tomando
    1.01
    ♗
    0.92
    匠
    0.92
     ance
    0.91
     concept
    0.91
     Cougar
    0.90
     vorgesehen
    0.90
     кү
    0.90
    思想
    0.89
     ances
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.