© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15309
    Prev
    Next
    INDEX
    Explanations

    our lives

    np_acts-logits-general · gemini-2.5-flash-lite

    colonialism, prescription, flat Earth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     跳转
    0.58
     时
    0.54
     Faculté
    0.52
     设备
    0.52
    টসম্যান
    0.52
     技术
    0.51
     获取
    0.50
     impeller
    0.50
     猫
    0.50
     neumáticos
    0.50
    POSITIVE LOGITS
    a
    0.54
    father
    0.50
    zt
    0.48
    He
    0.47
    derived
    0.46
    an
    0.45
    を感じ
    0.45
    violence
    0.45
    form
    0.45
    constitutional
    0.44
    Activations Density 0.001%

    No Known Activations