© 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. 31977
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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
     itself
    0.45
     товара
    0.39
    t
    0.38
     ஒன்று
    0.37
    IVIDUAL
    0.37
     aldığı
    0.37
     کرے
    0.36
    J
    0.36
     its
    0.35
    l
    0.35
    POSITIVE LOGITS
    দের
    0.58
    队的
    0.54
    队
    0.51
    들에게
    0.50
    们的
    0.50
    들의
    0.46
    们
    0.44
    隊
    0.44
     мають
    0.42
     precisam
    0.42
    Activations Density 0.004%

    No Known Activations