© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2233
    Prev
    Next
    INDEX
    Explanations

    am programmed to be safe

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     wd
    1.38
     viva
    1.25
    wax
    1.24
     $\#
    1.22
     xl
    1.22
    uously
    1.22
     expres
    1.21
    $$\
    1.21
    有名
    1.20
    issances
    1.20
    POSITIVE LOGITS
     Але
    0.88
    淘宝
    0.86
     Rezept
    0.86
    zerw
    0.85
     Бет
    0.77
    πι
    0.77
     giud
    0.76
     preço
    0.75
    Ara
    0.74
     Jeong
    0.74
    Activations Density 0.124%

    No Known Activations