© 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. 28801
    Prev
    Next
    INDEX
    Explanations

    cultures, vehicles, rivalry, called

    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
     ہمیں
    0.43
    🫠
    0.42
     uiteindelijk
    0.42
     درمیان
    0.40
     പ്രദേശ
    0.40
    ☯
    0.40
     انسان
    0.39
     logika
    0.39
    ейчас
    0.39
    ስቃ
    0.39
    POSITIVE LOGITS
     because
    0.47
    。
    0.46
     removing
    0.44
     。
    0.43
     importance
    0.43
    because
    0.42
     remove
    0.41
     Vì
    0.41
     不需要
    0.41
    importance
    0.40
    Activations Density 0.013%

    No Known Activations