© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13963
    Prev
    Next
    INDEX
    Explanations

    military service and conflicts

    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_22/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
    Normally
    -1.23
    Already
    -1.21
    年も
    -1.18
     suatu
    -1.14
     fãs
    -1.13
     flink
    -1.13
     zapatillas
    -1.12
     Deckel
    -1.11
    Hopefully
    -1.09
     давно
    -1.08
    POSITIVE LOGITS
     during
    1.95
     participated
    1.52
     participate
    1.38
     became
    1.26
     support
    1.23
     went
    1.20
     helped
    1.19
     when
    1.19
     actions
    1.18
     played
    1.16
    Activations Density 0.088%

    No Known Activations