© 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. 33334
    Prev
    Next
    INDEX
    Explanations

    military operations and raids

    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
     theft
    -0.84
     for
    -0.80
     ideas
    -0.79
    chinen
    -0.76
     lacer
    -0.75
     time
    -0.75
     Methods
    -0.74
     Events
    -0.73
    bourg
    -0.70
    国防
    -0.70
    POSITIVE LOGITS
     operation
    2.58
     operations
    2.17
    Operation
    2.05
    operation
    1.92
     Operation
    1.91
     OPERATION
    1.84
    OPERATION
    1.83
     opérations
    1.77
     opération
    1.73
     operasi
    1.73
    Activations Density 0.048%

    No Known Activations