© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13732
    Prev
    Next
    INDEX
    Explanations

    initial

    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_16k_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
    後
    0.41
     দক্ষি
    0.39
     позд
    0.38
     Liter
    0.37
    後に
    0.37
     الوحده
    0.36
     संसदीय
    0.36
    ῷ
    0.36
     सक्सेस
    0.36
     successivamente
    0.36
    POSITIVE LOGITS
     initial
    1.11
    Initial
    0.96
     اولیه
    0.94
    initial
    0.93
     upfront
    0.93
    前期
    0.93
     Initial
    0.92
     initiale
    0.89
     inicial
    0.88
    初始
    0.88
    Activations Density 1.392%

    No Known Activations