© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 70852
    Prev
    Next
    INDEX
    Explanations

    Georgia, George

    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
    ut
    0.48
     mapa
    0.45
    </h1>
    0.44
     varn
    0.44
    ↵
    0.42
     rhymes
    0.42
     suman
    0.42
     gods
    0.42
     cats
    0.40
    ers
    0.40
    POSITIVE LOGITS
     ڪر
    0.50
     Georg
    0.49
    marginX
    0.47
     Геор
    0.46
     রাস্ত
    0.45
    害怕
    0.44
    ക്കേണ്ട
    0.44
    Georgia
    0.43
    ᓪ
    0.43
    噰
    0.43
    Activations Density 0.015%

    No Known Activations