© 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. 7872
    Prev
    Next
    INDEX
    Explanations

    security vulnerabilities and updates

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

    security vulnerabilities

    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
    朐
    0.51
     Skating
    0.48
     bateau
    0.47
     نثر
    0.47
     ordination
    0.46
     seizoen
    0.46
     orderService
    0.46
    ཎ
    0.45
    ätten
    0.45
     сезо
    0.45
    POSITIVE LOGITS
     vulnerability
    0.90
    CVE
    0.89
     CVE
    0.89
     vulnerabilities
    0.88
     vulner
    0.83
     vuln
    0.79
     Vulner
    0.75
    漏洞
    0.75
     vulnerable
    0.71
     exploit
    0.68
    Activations Density 0.054%

    No Known Activations