© 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. 20361
    Prev
    Next
    INDEX
    Explanations

    security vulnerability detection

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

    issues, risks, and violations

    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
    佉
    0.50
     extraordinaria
    0.47
     fillColorSpace
    0.46
    敍
    0.46
     роман
    0.46
    钥匙
    0.46
     servici
    0.45
    鍵
    0.45
    лога
    0.44
    籟
    0.44
    POSITIVE LOGITS
     violations
    0.88
     detect
    0.82
     Warnings
    0.82
     detected
    0.77
    warnings
    0.77
     warnings
    0.77
     Severity
    0.75
     violation
    0.75
     detects
    0.75
     violated
    0.74
    Activations Density 0.058%

    No Known Activations