© 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-262K
    7. 58566
    Prev
    Next
    INDEX
    Explanations

    ministry and its departments

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

    government ministries

    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_262k_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
    𝙡
    0.55
    🦴
    0.55
     perros
    0.51
     серде
    0.51
     परीक्षण
    0.51
     chiens
    0.50
     ቫ
    0.50
    𝙍
    0.50
    𝟖
    0.50
     соба
    0.49
    POSITIVE LOGITS
     Ministry
    0.82
     Minister
    0.81
     minister
    0.81
     ministry
    0.78
    Ministry
    0.77
    Minister
    0.76
     Ministers
    0.74
    Minist
    0.72
     وزارت
    0.71
    minister
    0.71
    Activations Density 0.025%

    No Known Activations