© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68183
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    ık
    -0.97
     خبرگزاری
    -0.92
    aruhi
    -0.91
    鹹
    -0.88
     całego
    -0.88
    почки
    -0.87
    ījum
    -0.86
    entsch
    -0.86
     Larg
    -0.85
     spiegel
    -0.85
    POSITIVE LOGITS
     nörd
    1.19
    硃
    1.03
    urz
    1.00
     süd
    0.97
     nacer
    0.97
     行っ
    0.96
     نوف
    0.93
    Catatan
    0.93
    afternoon
    0.93
    Massa
    0.92
    Activations Density 0.031%

    No Known Activations