© 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-65K
    7. 53466
    Prev
    Next
    INDEX
    Explanations

    desperate smugglers, lavender products

    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_65k_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
    들이
    0.45
    lympi
    0.45
    бири
    0.42
     bölges
    0.40
    lös
    0.40
    сто
    0.39
    केवल
    0.39
     및
    0.38
    appara
    0.38
    了
    0.38
    POSITIVE LOGITS
     onboarding
    0.48
     Snapchat
    0.47
     microphones
    0.46
     smart
    0.46
     pajamas
    0.45
     bullying
    0.44
     ভাঁ
    0.44
     emoji
    0.43
     emojis
    0.43
     sofá
    0.43
    Activations Density 0.002%

    No Known Activations