© 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. 34-GEMMASCOPE-RES-131K
    7. 91866
    Prev
    Next
    INDEX
    Explanations

    gun violence and control

    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
     firearms
    -0.89
     garagem
    -0.81
     zakresie
    -0.78
    Ngh
    -0.78
    Vous
    -0.77
    Painting
    -0.77
    ogne
    -0.77
    isième
    -0.77
    ouf
    -0.77
     Bibel
    -0.76
    POSITIVE LOGITS
     violence
    0.81
     manufacturers
    0.80
     sale
    0.79
    されています
    0.75
    Tito
    0.74
    รวจ
    0.74
    測試
    0.73
    Grap
    0.73
     delitos
    0.72
     play
    0.71
    Activations Density 0.021%

    No Known Activations