© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71601
    Prev
    Next
    INDEX
    Explanations

    occupations and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    J
    -1.88
    D
    -1.88
    T
    -1.87
    ’
    -1.86
    P
    -1.81
    ‘
    -1.79
     The
    -1.72
    N
    -1.70
     and
    -1.69
    L
    -1.69
    POSITIVE LOGITS
    Rumah
    1.73
    Suka
    1.73
    Warna
    1.63
    Baru
    1.62
    Makan
    1.59
    хані
    1.54
    Reaper
    1.54
    Fungsi
    1.53
    xique
    1.52
    Bahan
    1.51
    Activations Density 0.046%

    No Known Activations