© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3479
    Prev
    Next
    INDEX
    Explanations

    DNS Leak, WikiLeaks

    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_29_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
    suspended
    0.67
    粧
    0.66
    麿
    0.66
    iella
    0.65
    攪
    0.64
    óm
    0.63
    transformed
    0.62
    斓
    0.61
     RAI
    0.61
    imps
    0.60
    POSITIVE LOGITS
     leak
    3.20
     leaking
    3.11
     leaks
    3.09
     leakage
    3.09
     Leak
    2.98
    Leak
    2.90
    leak
    2.80
     leaked
    2.64
    泄漏
    2.56
     leaky
    2.40
    Activations Density 0.328%

    No Known Activations