© 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. 57061
    Prev
    Next
    INDEX
    Explanations

    Embedding

    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
    Jazz
    0.46
     fade
    0.43
    ありがとう
    0.43
    ЛИ
    0.43
    ંધ
    0.43
    কারি
    0.42
    ྨ
    0.42
    🎟
    0.42
     હજાર
    0.42
    赋值
    0.41
    POSITIVE LOGITS
     Mejor
    0.49
     Guill
    0.49
     Chinn
    0.47
     Еў
    0.46
     informs
    0.46
     أفضل
    0.45
     chicas
    0.45
     ис
    0.45
     청
    0.45
    ى
    0.45
    Activations Density 0.001%

    No Known Activations