© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7993
    Prev
    Next
    INDEX
    Explanations

    evading detection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    в
    0.89
    旁邊
    0.80
    ત્મક
    0.80
    ructive
    0.79
     Neville
    0.79
    świad
    0.78
     व्यावहारिक
    0.77
     Sphere
    0.77
    ਯ
    0.76
     affirmations
    0.76
    POSITIVE LOGITS
     evade
    1.23
     fleeing
    1.23
    逃
    1.22
    追踪
    1.22
     manh
    1.21
     detection
    1.20
     criminals
    1.19
     fugit
    1.19
    detection
    1.18
     getaway
    1.17
    Activations Density 0.103%

    No Known Activations