© 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. 125789
    Prev
    Next
    INDEX
    Explanations

    verdicts mixed, compression, avoids copying

    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
     શ
    0.50
     elixir
    0.50
     The
    0.44
     எதிர
    0.44
     অংশ
    0.43
     N
    0.42
    ppers
    0.41
     $$
    0.41
    </b>
    0.41
     W
    0.40
    POSITIVE LOGITS
     سانس
    0.53
     humedad
    0.51
    annulation
    0.50
    ні
    0.49
     judiciaire
    0.48
    伲
    0.48
     diminta
    0.47
     Compression
    0.46
    ኵ
    0.46
     جاتا
    0.45
    Activations Density 0.002%

    No Known Activations