© 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. 60406
    Prev
    Next
    INDEX
    Explanations

    talk and conversation

    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
    ဇ
    -0.75
    вила
    -0.75
    meester
    -0.69
     dobu
    -0.67
     pinch
    -0.67
     adul
    -0.66
     calma
    -0.66
     Сла
    -0.66
     estan
    -0.65
     transients
    -0.65
    POSITIVE LOGITS
     talk
    2.20
     verbose
    2.05
     chatter
    2.03
    talk
    1.91
     TALK
    1.80
     Talk
    1.79
    Talk
    1.74
    Verbose
    1.68
     chat
    1.68
     talking
    1.68
    Activations Density 0.024%

    No Known Activations