© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11952
    Prev
    Next
    INDEX
    Explanations

    refusing dangerous instructions/information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    恨
    1.13
    のですが
    1.12
     আশ্রম
    1.09
    很多的
    1.07
    んですが
    1.06
    LIKE
    1.05
    HEIM
    1.04
    ヴァン
    1.04
    CAUSE
    1.04
    Incidentally
    1.04
    POSITIVE LOGITS
     ≥
    1.03
     or
    0.95
     ≤
    0.95
     eller
    0.93
     *.
    0.93
     +.
    0.88
     ±
    0.88
     flammable
    0.88
    existent
    0.88
     mindestens
    0.87
    Activations Density 0.171%

    No Known Activations