© 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. 65494
    Prev
    Next
    INDEX
    Explanations

    list items separated by periods

    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
     piè
    0.46
     разговор
    0.44
     traditionnel
    0.42
    歉
    0.41
     ήταν
    0.40
     restrooms
    0.40
     ersten
    0.40
     tế
    0.39
     chuyện
    0.39
     Decorative
    0.39
    POSITIVE LOGITS
    aku
    0.37
     push
    0.36
     ܘ
    0.36
    ไฮ
    0.36
    deki
    0.35
     Gym
    0.35
    ill
    0.35
     copper
    0.35
     importantly
    0.34
     Flex
    0.34
    Activations Density 0.002%

    No Known Activations