© 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-16K
    7. 9211
    Prev
    Next
    INDEX
    Explanations

    Recommendation Systems

    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_16k_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
     ব্যায়াম
    0.47
     cuisson
    0.46
     व्यायाम
    0.45
     imbib
    0.43
    安裝
    0.43
     stow
    0.41
    jeno
    0.41
     깨
    0.40
     অত্যন্ত
    0.40
     изделия
    0.40
    POSITIVE LOGITS
     matchmaking
    1.02
     broker
    0.80
    匹配
    0.80
     Matching
    0.79
     brokerage
    0.78
     matching
    0.75
    Matching
    0.75
    マッチ
    0.73
     brok
    0.72
    matching
    0.71
    Activations Density 0.257%

    No Known Activations