© 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. 34-GEMMASCOPE-RES-131K
    7. 98869
    Prev
    Next
    INDEX
    Explanations

    Isle of Man

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    〗
    -0.76
    叶子
    -0.75
     człowie
    -0.75
     relying
    -0.73
    ดง
    -0.72
    тов
    -0.71
     Rivas
    -0.71
    коны
    -0.71
     diamante
    -0.71
     Sani
    -0.70
    POSITIVE LOGITS
     IOM
    1.19
    IOM
    1.15
     Isle
    1.05
     Lax
    1.03
     Ramsey
    1.02
    iom
    0.90
     Peel
    0.88
    Isle
    0.88
    Lax
    0.85
    isle
    0.84
    Activations Density 0.012%

    No Known Activations