© 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. 76024
    Prev
    Next
    INDEX
    Explanations

    desertion and defection

    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
     toxicity
    -1.37
     toxic
    -1.20
     Toxicity
    -1.07
     Toxic
    -1.04
    toxic
    -0.98
    toxicity
    -0.90
    Toxic
    -0.89
     tóxic
    -0.86
     TOXIC
    -0.82
     токси
    -0.77
    POSITIVE LOGITS
     desertion
    3.28
     deser
    3.28
     desert
    3.11
     deserted
    2.67
     deserts
    2.39
    desert
    2.38
     Desert
    2.20
    Desert
    2.17
     mutiny
    1.91
     AW
    1.84
    Activations Density 0.033%

    No Known Activations