© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 15731
    Prev
    Next
    INDEX
    Explanations

    safety and security related terms

    np_acts-logits-general · gemini-2.5-flash-lite

    safety and risk mitigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     экономических
    0.50
     bookstores
    0.50
     rohkem
    0.50
     исторических
    0.46
     bookstore
    0.45
     मानता
    0.45
     पाने
    0.45
     책
    0.45
     झग
    0.45
    ные
    0.44
    POSITIVE LOGITS
     safety
    0.57
    安全
    0.53
    Safety
    0.52
     SAFETY
    0.51
     bezpečnost
    0.50
    SAFETY
    0.50
     Safety
    0.49
    HTMLElement
    0.46
     biztons
    0.46
    safety
    0.45
    Activations Density 0.000%

    No Known Activations