© 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. 38155
    Prev
    Next
    INDEX
    Explanations

    knife attacks and violence

    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
    בש
    -0.76
    GM
    -0.69
    ään
    -0.67
    POSURE
    -0.66
    腾讯
    -0.66
     brilliant
    -0.65
    烹饪
    -0.65
     rati
    -0.65
     coronation
    -0.64
     GM
    -0.64
    POSITIVE LOGITS
     knife
    1.27
    knife
    1.10
     attacker
    1.09
     kn
    1.07
    Knife
    1.05
     beheaded
    1.05
     stabbing
    1.00
     knives
    0.94
     Knife
    0.88
     kni
    0.87
    Activations Density 0.022%

    No Known Activations