© 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. 119084
    Prev
    Next
    INDEX
    Explanations

    affirmative answers to questions

    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
    lanations
    -0.90
     Explanation
    -0.89
     explanations
    -0.85
     explanation
    -0.77
    toxicity
    -0.73
     terrible
    -0.72
     Explained
    -0.70
    väll
    -0.69
     Segel
    -0.69
     spiega
    -0.69
    POSITIVE LOGITS
     affirmative
    3.73
    affirm
    2.78
     affirm
    2.67
     Affirmative
    2.64
    Affirm
    2.50
     negative
    2.23
     afirm
    1.95
     positive
    1.95
     affirming
    1.88
    negative
    1.86
    Activations Density 0.024%

    No Known Activations