© 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. 99557
    Prev
    Next
    INDEX
    Explanations

    proportion and ratio

    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
     രാഷ്ട്രീയ
    0.43
     arranc
    0.42
    acos
    0.40
     الأح
    0.39
     raping
    0.39
    ስ
    0.38
    lorescence
    0.38
     freund
    0.37
    ٹنے
    0.37
     উপেক্ষা
    0.37
    POSITIVE LOGITS
    ać
    0.51
    proportion
    0.50
    ed
    0.49
    al
    0.49
    ’
    0.47
     (%)
    0.47
    难题
    0.47
    尺
    0.46
     Proportion
    0.45
    ember
    0.45
    Activations Density 0.011%

    No Known Activations