© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 137023
    Prev
    Next
    INDEX
    Explanations

    heaven and afterlife concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_width_262k_l0_small_affine
    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
    กัด
    0.42
    ദേശ
    0.41
     infant
    0.38
     paj
    0.38
    囲
    0.37
     qualitative
    0.37
     beds
    0.36
    汔
    0.36
     qual
    0.36
     infield
    0.36
    POSITIVE LOGITS
     heavenly
    0.62
     Heavenly
    0.61
     Heaven
    0.61
    Heaven
    0.59
    heaven
    0.57
     небе
    0.56
    上帝
    0.55
     celestial
    0.54
     heaven
    0.54
     하나님
    0.54
    Activations Density 0.001%

    No Known Activations