© 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. 107589
    Prev
    Next
    INDEX
    Explanations

    firearm possession

    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
    受害
    -0.92
    ępu
    -0.78
     victims
    -0.77
     Однако
    -0.76
    被害
    -0.73
    верху
    -0.69
     vítima
    -0.68
    victim
    -0.68
    Victim
    -0.68
    upt
    -0.67
    POSITIVE LOGITS
     gun
    1.09
     ammunition
    1.06
     possession
    1.03
     prohibited
    1.01
     ammo
    0.92
     Possession
    0.88
     illegal
    0.88
     armat
    0.88
     Arms
    0.87
    possession
    0.87
    Activations Density 0.012%

    No Known Activations