© 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. 25779
    Prev
    Next
    INDEX
    Explanations

    semicolons and braces

    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
    tB
    -0.92
    着
    -0.90
     erhöhen
    -0.90
     is
    -0.89
    遭受
    -0.87
    fohl
    -0.87
     tämän
    -0.86
     которое
    -0.84
    Right
    -0.84
    的是
    -0.84
    POSITIVE LOGITS
    ÍC
    1.04
     Président
    1.04
    ógicos
    1.02
     metter
    0.99
     lapin
    0.96
     portait
    0.95
     alem
    0.93
    Более
    0.92
     Guimarães
    0.92
     hasard
    0.91
    Activations Density 0.039%

    No Known Activations