© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46206
    Prev
    Next
    INDEX
    Explanations

    r-initialisms and abbreviations

    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
    u
    0.96
    म
    0.90
    0
    0.90
    य
    0.88
     salen
    0.80
    م
    0.79
    ق
    0.76
     regularity
    0.76
    ف
    0.74
    ﺭ
    0.72
    POSITIVE LOGITS
    ется
    1.04
    al
    1.02
    ет
    0.91
    ى
    0.84
    all
    0.83
    )，
    0.82
    ،
    0.82
     are
    0.81
    ين
    0.77
    getR
    0.75
    Activations Density 0.152%

    No Known Activations