© 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-65K
    7. 56425
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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_65k_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
    hdr
    0.39
    軧
    0.39
    PropertySheets
    0.36
     Tub
    0.36
     Dire
    0.35
    hyde
    0.35
     Oversight
    0.35
    羙
    0.35
    िखित
    0.34
    MinWidth
    0.34
    POSITIVE LOGITS
     twice
    0.71
    两次
    0.59
    twice
    0.57
     zweimal
    0.57
     doble
    0.54
     pair
    0.53
    同士
    0.49
     दोन्ही
    0.49
     thrice
    0.48
     Twice
    0.48
    Activations Density 0.186%

    No Known Activations