© 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. 40-GEMMASCOPE-2-RES-262K
    7. 13948
    Prev
    Next
    INDEX
    Explanations

    historical periods and centuries

    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_40_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
    昭和
    0.52
     ಸಿನಿ
    0.50
     소련
    0.50
     کراچی
    0.47
     صنعتی
    0.46
    reetype
    0.45
    🐨
    0.45
    ็ก
    0.45
     soviet
    0.45
    ographystyle
    0.45
    POSITIVE LOGITS
     Renaissance
    1.33
     sixteenth
    1.30
     Elizabethan
    1.30
     seventeenth
    1.16
     Reformation
    1.10
     Tudor
    1.09
     XVI
    1.07
    Rena
    1.07
     XVII
    1.03
     Baroque
    1.00
    Activations Density 0.047%

    No Known Activations