© 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. 65730
    Prev
    Next
    INDEX
    Explanations

    for ( loop

    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
     eventually
    -0.96
     somethin
    -0.91
     spune
    -0.90
     trebui
    -0.88
     نوف
    -0.87
     something
    -0.87
     pouze
    -0.85
    
    -0.85
    りたい
    -0.84
     Lastly
    -0.84
    POSITIVE LOGITS
     each
    1.66
     (
    1.52
     Each
    1.25
    Each
    1.25
    each
    1.23
     EACH
    1.12
     chaque
    1.05
     каждому
    0.99
    forEach
    0.95
    每個
    0.94
    Activations Density 0.005%

    No Known Activations