© 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. 93947
    Prev
    Next
    INDEX
    Explanations

    it's fair or safe to say

    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
     menik
    -0.91
     häng
    -0.88
    лта
    -0.78
    cially
    -0.76
     quartier
    -0.74
    afternoon
    -0.73
     château
    -0.72
    ;;)
    -0.72
    ++.
    -0.71
    ilets
    -0.70
    POSITIVE LOGITS
     fair
    4.25
    fair
    2.70
     safe
    2.58
    Fair
    2.55
     Fair
    2.34
     fairs
    2.25
    FAIR
    2.19
     FAIR
    2.14
     fairness
    1.97
     accurate
    1.70
    Activations Density 0.030%

    No Known Activations