© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2124
    Prev
    Next
    INDEX
    Explanations

    submission and obedience

    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_17_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
    探讨
    1.09
     troubleshooting
    1.02
    争议
    1.01
    炒
    1.01
     extrapolated
    0.98
     démar
    0.97
    事故
    0.97
    創業
    0.97
     चर्चित
    0.95
    砭
    0.94
    POSITIVE LOGITS
     obedient
    2.24
     obedience
    2.23
     obed
    2.04
     subserv
    2.04
     obeying
    1.97
     obey
    1.96
     obeys
    1.87
     Obed
    1.84
    obedience
    1.83
     submission
    1.77
    Activations Density 0.585%

    No Known Activations