© 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. 32883
    Prev
    Next
    INDEX
    Explanations

    Uma and names beginning with Um

    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
    ěry
    -0.85
    tuje
    -0.80
     Mancha
    -0.79
     moky
    -0.73
    gub
    -0.72
    聩
    -0.71
     légère
    -0.71
    kü
    -0.71
     Binding
    -0.70
    лах
    -0.70
    POSITIVE LOGITS
     stupidity
    0.67
    engr
    0.66
    
    0.63
    umable
    0.62
     determinada
    0.61
     Dag
    0.61
    toupper
    0.61
    Daughter
    0.60
     nour
    0.60
     cô
    0.59
    Activations Density 0.038%

    No Known Activations