© 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-262K
    7. 34752
    Prev
    Next
    INDEX
    Explanations

    time, presence, ingredients, coding, sleep

    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_262k_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
     어떤
    0.46
    ၊
    0.45
     yapılacak
    0.44
     básicas
    0.43
     자동차
    0.43
    个
    0.43
     automakers
    0.41
    িল
    0.40
    ukebox
    0.40
     airport
    0.40
    POSITIVE LOGITS
     🎉
    0.46
     venge
    0.43
     equaling
    0.43
     Kn
    0.42
     écl
    0.41
     heavily
    0.41
     শুনেছি
    0.41
     smug
    0.41
     succede
    0.41
     Matcha
    0.39
    Activations Density 0.003%

    No Known Activations