© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 2184
    Prev
    Next
    INDEX
    Explanations

    references to contextually appropriate terms, ideas, or concepts for specific types of content, such as social media posts, articles, or narratives.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    events or descriptions of states

    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
    ۔
    0.37
     eğer
    0.32
    یں۔
    0.32
    妣
    0.31
     اپنے
    0.29
     allemaal
    0.29
     wenn
    0.29
    自己的
    0.29
     ако
    0.29
    \
    0.28
    POSITIVE LOGITS
     exists
    0.49
     abound
    0.49
     ensues
    0.44
     occurred
    0.44
     ensued
    0.44
     occurs
    0.43
     arose
    0.42
     arises
    0.42
     prevails
    0.40
     arise
    0.40
    Activations Density 0.258%

    No Known Activations