© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12750
    Prev
    Next
    INDEX
    Explanations

    presidential and charitable initiatives

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

    presidential figures and government offices

    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_31_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
     visionary
    0.49
     hegemony
    0.43
     Englishman
    0.42
     başında
    0.41
    계
    0.41
     MANUFACTURING
    0.40
     Aztecs
    0.40
    දු
    0.39
     industria
    0.39
     worded
    0.39
    POSITIVE LOGITS
    宫
    0.55
    protocol
    0.53
     Presidential
    0.52
    摄影
    0.46
    协议
    0.46
    VIP
    0.46
     presidencial
    0.46
    总统
    0.45
    有趣
    0.45
    陪伴
    0.45
    Activations Density 0.130%

    No Known Activations