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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14539
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    np_acts-logits-general · gemini-2.5-flash-lite

    numeric codes and addresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ת
    1.06
    ل
    1.04
    ל
    1.02
    ت
    0.96
    ع
    0.95
    ע
    0.92
    تين
    0.87
    ד
    0.84
    أي
    0.82
    عة
    0.78
    POSITIVE LOGITS
    <0x80>
    0.98
    0
    0.90
    ्य
    0.81
    za
    0.79
    chrom
    0.79
    ff
    0.77
    *
    0.75
    ),
    0.74
    ffic
    0.71
    '
    0.70
    Activations Density 3.421%

    No Known Activations