© 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. 84887
    Prev
    Next
    INDEX
    Explanations

    pauses before speaking

    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
    comments
    -0.87
     comentarios
    -0.83
    
    -0.81
    writes
    -0.80
     yells
    -0.78
     Comment
    -0.77
     Reply
    -0.77
    Comments
    -0.77
     ensimmä
    -0.77
     поз
    -0.76
    POSITIVE LOGITS
     pause
    2.41
     paused
    2.41
     pauses
    2.11
    pause
    2.11
     pausing
    1.90
    Pause
    1.85
     pausa
    1.74
     Pause
    1.70
    PAUSE
    1.63
    paused
    1.54
    Activations Density 0.008%

    No Known Activations