© 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. 3392
    Prev
    Next
    INDEX
    Explanations

    content related to specific types of leave and absence policies in a workplace.

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

    if you

    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
     aussi
    0.32
    beiten
    0.30
    রাও
    0.30
    勮
    0.30
     সরিয়ে
    0.30
    ).
    0.29
    μενο
    0.28
    癃
    0.28
     җиңү
    0.28
     также
    0.27
    POSITIVE LOGITS
     you
    0.56
    you
    0.47
     você
    0.46
     хотите
    0.44
     તમે
    0.41
     bạn
    0.41
    un
    0.41
    ac
    0.41
     আপনি
    0.40
     youre
    0.40
    Activations Density 0.109%

    No Known Activations