© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6498
    Prev
    Next
    INDEX
    Explanations

    pen prefix

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

    penetration testing or pen name

    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_53_width_65k_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
    昙
    0.46
    لع
    0.39
     Подо
    0.39
     intense
    0.38
    ឹ
    0.38
    dU
    0.38
     Violation
    0.38
    𒅖
    0.37
     vari
    0.37
     forced
    0.37
    POSITIVE LOGITS
    Pen
    0.95
    PEN
    0.93
     pen
    0.92
     PEN
    0.90
     пен
    0.84
     Pen
    0.82
     pén
    0.80
     পেন
    0.78
    elope
    0.77
    pen
    0.77
    Activations Density 0.030%

    No Known Activations