© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84712
    Prev
    Next
    INDEX
    Explanations

    wide receiver, dimensions

    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_10/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
    >
    -3.55
     a
    -3.03
    ’
    -2.88
    {
    -2.77
    <
    -2.61
    ↵
    -2.59
    U
    -2.48
     to
    -2.45
     l
    -2.44
     don
    -2.44
    POSITIVE LOGITS
     Anſ
    3.09
    Kondisi
    3.06
    Ukuran
    3.00
    Proses
    2.95
    Semua
    2.94
    Tujuan
    2.86
    Tahun
    2.77
    Tempat
    2.75
    Tidak
    2.75
    Fitur
    2.73
    Activations Density 0.027%

    No Known Activations