© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 165313
    Prev
    Next
    INDEX
    Explanations

    splitting into parts

    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_40_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
     "\
    0.41
    comboBox
    0.40
    ("\
    0.39
    ದಾರ
    0.38
    ($"
    0.37
    िने
    0.37
    બંધ
    0.37
    ="$
    0.36
     সম্মিল
    0.36
     bein
    0.36
    POSITIVE LOGITS
     segments
    0.65
     sections
    0.62
     segmentos
    0.58
     section
    0.57
     الجزء
    0.56
     portions
    0.55
     část
    0.55
     segment
    0.54
     secciones
    0.54
     portion
    0.54
    Activations Density 0.048%

    No Known Activations