© 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. 16-GEMMASCOPE-2-RES-262K
    7. 103868
    Prev
    Next
    INDEX
    Explanations

    under- prefix compounds

    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_16_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
    u
    0.82
    an
    0.80
    ח
    0.80
    ↵↵
    0.77
    ו
    0.76
    m
    0.75
    نا
    0.74
    as
    0.72
    os
    0.71
    )。
    0.66
    POSITIVE LOGITS
     〢
    1.15
     ﺍ
    0.91
     ރ
    0.87
     緊急
    0.84
     posticis
    0.83
     ຮ
    0.83
     忄
    0.83
     ក
    0.82
     අඩු
    0.81
    lular
    0.80
    Activations Density 0.008%

    No Known Activations