© 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. 11863
    Prev
    Next
    INDEX
    Explanations

    worth pausing to consider

    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
    ]=(
    -0.87
     monter
    -0.84
     stras
    -0.83
    Tembelea
    -0.83
    änglich
    -0.83
    ;</
    -0.79
     サム
    -0.79
    
    -0.79
    Athens
    -0.77
    joyed
    -0.77
    POSITIVE LOGITS
     pause
    3.91
     pausing
    3.14
    pause
    3.03
     paused
    3.02
     stop
    3.02
     pauses
    2.84
    Pause
    2.83
     Pause
    2.80
     step
    2.66
    stop
    2.45
    Activations Density 0.043%

    No Known Activations