© 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. 56863
    Prev
    Next
    INDEX
    Explanations

    transportation methods

    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
    ભ
    0.47
    ativos
    0.45
     unquestion
    0.44
    ਾਰੇ
    0.43
     markedly
    0.42
    atividade
    0.42
     типи
    0.41
    咭
    0.41
     صاح
    0.41
     Patrimonio
    0.41
    POSITIVE LOGITS
    飞行
    0.44
     刺繍
    0.44
     سلاټ
    0.41
    νος
    0.40
     ervoor
    0.40
    开头
    0.40
    🛳
    0.40
    อื่น
    0.40
     ভ্রমণ
    0.40
     بیټینګ
    0.39
    Activations Density 0.002%

    No Known Activations