© 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. 110871
    Prev
    Next
    INDEX
    Explanations

    oral traditions, long term consequence

    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
    О
    0.54
    И
    0.47
    Ф
    0.44
    ιδ
    0.43
    Ш
    0.43
    파
    0.42
    Π
    0.41
     nombreuses
    0.41
    Universe
    0.41
    А
    0.41
    POSITIVE LOGITS
     দেখেছি
    0.50
     posterity
    0.46
     senere
    0.44
     कर्त
    0.44
     Plugins
    0.44
     ihan
    0.43
     Proto
    0.43
    ्हान
    0.42
     Eds
    0.42
     Goog
    0.42
    Activations Density 0.009%

    No Known Activations