© 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. 82438
    Prev
    Next
    INDEX
    Explanations

    pepper spray, tear gas, stun

    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
     beheaded
    -0.95
     slaughtered
    -0.90
     Alc
    -0.84
    killed
    -0.80
    吞噬
    -0.79
     plunged
    -0.76
     underside
    -0.76
     intestine
    -0.73
     bombings
    -0.73
     killed
    -0.72
    POSITIVE LOGITS
     pepper
    2.30
     Pepper
    1.87
    pepper
    1.76
     mace
    1.57
    Pepper
    1.55
     stun
    1.44
     Mace
    1.40
    Mace
    1.33
     peppers
    1.28
     tas
    1.25
    Activations Density 0.020%

    No Known Activations