© 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. 103773
    Prev
    Next
    INDEX
    Explanations

    Maybe, date, search

    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
    risti
    -0.84
     changes
    -0.79
     Non
    -0.77
     could
    -0.75
     both
    -0.75
     Content
    -0.73
     by
    -0.71
     disputes
    -0.71
     creates
    -0.71
     Stirn
    -0.70
    POSITIVE LOGITS
     getPath
    0.96
    чению
    0.92
     behalf
    0.85
    Belgique
    0.85
     vendeurs
    0.84
     jurist
    0.84
    駙
    0.83
    Spolja
    0.83
    卖
    0.82
    ורת
    0.82
    Activations Density 0.001%

    No Known Activations