© 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. 18428
    Prev
    Next
    INDEX
    Explanations

    verify that, crimes, chance

    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
     electricidad
    0.55
     نہيں
    0.53
    ὀ
    0.52
    ₕ
    0.49
     دليل
    0.49
    埥
    0.48
    botones
    0.48
     الخاصة
    0.47
     تركيب
    0.47
    ʃ
    0.47
    POSITIVE LOGITS
     countries
    0.47
     about
    0.45
    *
    0.44
    บาง
    0.44
    ดี
    0.44
    “
    0.44
    不如
    0.43
    อ
    0.43
    Hungary
    0.43
    ;
    0.43
    Activations Density 0.000%

    No Known Activations