© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79362
    Prev
    Next
    INDEX
    Explanations

    numbers in brackets

    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
    Negative Logits
    桧
    -0.98
    ,”
    -0.89
    Luckily
    -0.87
    Materiał
    -0.83
     something
    -0.82
    ),'
    -0.82
    Anything
    -0.81
     anything
    -0.80
    Zalety
    -0.80
     Finally
    -0.79
    POSITIVE LOGITS
    ↵↵↵↵↵↵↵
    1.20
    ↵↵↵↵↵↵↵↵↵
    1.14
    ↵↵↵↵↵↵↵↵↵↵
    1.12
    ↵↵↵↵
    1.09
    ↵↵↵↵↵↵↵↵↵↵↵↵
    1.07
    ↵↵↵↵↵↵↵↵↵↵↵
    1.05
     Contents
    1.03
    Contents
    1.02
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.00
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.99
    Activations Density 0.253%

    No Known Activations