© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17372
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iremos
    0.47
     بلوچ
    0.47
    isSignedIn
    0.44
     שהוא
    0.43
    簇
    0.43
    غانستان
    0.42
     الكويت
    0.42
    لينكات
    0.41
     भूटान
    0.41
    ଞ
    0.41
    POSITIVE LOGITS
     Roman
    1.14
     рим
    1.10
     Hadrian
    0.95
     Rome
    0.90
     रोमन
    0.88
     röm
    0.87
    Roman
    0.87
     Romans
    0.82
    ローマ
    0.82
     Emperor
    0.80
    Activations Density 0.149%

    No Known Activations