© 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. 98102
    Prev
    Next
    INDEX
    Explanations

    president and their departments

    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
    ことは
    -0.81
     vs
    -0.80
    oko
    -0.78
     comforting
    -0.78
     settembre
    -0.77
    杜
    -0.76
     kick
    -0.75
     recib
    -0.73
     の
    -0.71
    núť
    -0.70
    POSITIVE LOGITS
     Operations
    1.50
     operations
    1.49
    Operations
    1.39
     OPERATIONS
    1.20
    operations
    1.13
     Strategy
    1.04
     Administration
    1.01
     finance
    0.98
     finances
    0.98
    OPER
    0.96
    Activations Density 0.018%

    No Known Activations