© 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. 17372
    Prev
    Next
    INDEX
    Explanations

    Roman Empire and history

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

    Roman Empire history

    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
     дизайне
    0.52
     வாழைப்பழ
    0.51
     بلوچ
    0.50
    ۹
    0.50
     ecológica
    0.49
    簇
    0.48
    لينكات
    0.48
    𝚢
    0.48
    鸫
    0.47
    نو
    0.47
    POSITIVE LOGITS
     Roman
    1.24
     рим
    1.21
     Rome
    1.02
     Hadrian
    1.02
     Romans
    0.96
    Roman
    0.95
     रोमन
    0.95
     Pompe
    0.92
     röm
    0.92
     roman
    0.92
    Activations Density 0.058%

    No Known Activations