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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 16918
    Prev
    Next
    INDEX
    Explanations

    governance and policies

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

    policy and future promises

    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
     加工
    0.42
    𝗆
    0.41
    精度
    0.40
    farande
    0.39
     உச்ச
    0.39
     औपचारिक
    0.39
    誂
    0.39
    畸
    0.39
     습
    0.38
     Formal
    0.38
    POSITIVE LOGITS
     policies
    0.97
    policies
    0.94
     governance
    0.93
    Policies
    0.89
     Policies
    0.88
     정책
    0.83
     policym
    0.82
    정책
    0.82
    Governance
    0.81
     Governance
    0.81
    Activations Density 0.122%

    No Known Activations