© 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. 34-GEMMASCOPE-RES-131K
    4. 33064
    Prev
    Next
    INDEX
    Explanations

    secure followed by context

    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
     succinctly
    -1.03
     Its
    -1.01
    rófono
    -0.98
     incessantly
    -0.96
    órnio
    -0.95
    textAlign
    -0.94
     afectan
    -0.94
     Bescheid
    -0.93
    sider
    -0.93
    znego
    -0.93
    POSITIVE LOGITS
     footing
    1.28
    ly
    1.05
    guarded
    0.95
    messaging
    0.94
    ties
    0.91
     COMPOUNDS
    0.90
     transactions
    0.87
     messaging
    0.87
     Swami
    0.87
    bolista
    0.85
    Activations Density 0.017%

    No Known Activations