© 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-262K
    7. 12846
    Prev
    Next
    INDEX
    Explanations

    or auxiliary verb

    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
    December
    0.49
     в
    0.44
     derfor
    0.42
    মিত
    0.41
    Conv
    0.41
     البته
    0.41
    ",
    0.41
    То
    0.41
    ),
    0.41
    В
    0.41
    POSITIVE LOGITS
    只是
    0.70
     chỉ
    0.64
     only
    0.57
     শুধু
    0.55
     tylko
    0.54
     শুধ
    0.53
     sadece
    0.50
     just
    0.50
     csak
    0.50
     hanya
    0.49
    Activations Density 0.020%

    No Known Activations