© 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. 47775
    Prev
    Next
    INDEX
    Explanations

    or ear

    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
     sagt
    0.42
     Scher
    0.42
     example
    0.42
     ausges
    0.41
    烀
    0.41
    どう
    0.39
    並沒有
    0.39
     Основ
    0.38
    焦点
    0.38
    例
    0.38
    POSITIVE LOGITS
     노래
    0.40
    호를
    0.39
    হাকে
    0.39
     鞋
    0.39
     रहो
    0.37
     developmentally
    0.37
    utel
    0.36
     ভিন্ন
    0.35
    高的
    0.35
     więks
    0.35
    Activations Density 0.001%

    No Known Activations