© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 16571
    Prev
    Next
    INDEX
    Explanations

    privilege escalation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    1.63
    il
    1.27
    is
    1.23
     a
    1.22
     be
    1.21
    et
    1.17
    ها
    1.16
     at
    1.15
    land
    1.13
    ं
    1.13
    POSITIVE LOGITS
     privil
    1.60
     privileges
    1.51
     privilege
    1.36
     privilegio
    1.35
    و
    1.29
     privileged
    1.27
     Privilege
    1.20
     privile
    1.05
    <0x0D>
    1.03
     obscures
    1.00
    Activations Density 0.003%

    No Known Activations