© 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. 34-GEMMASCOPE-RES-131K
    7. 33732
    Prev
    Next
    INDEX
    Explanations

    special characters after words

    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_34/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
     from
    -0.99
     which
    -0.95
    ូ
    -0.87
     mógł
    -0.83
     Ně
    -0.83
    homem
    -0.82
    Uli
    -0.81
    Organis
    -0.81
     probably
    -0.80
    vı
    -0.80
    POSITIVE LOGITS
    both
    1.09
    trailing
    0.97
    γει
    0.96
     ,,
    0.94
    ทั้ง
    0.94
    !!!!!!!
    0.94
    もちろん
    0.92
    !!!!!!
    0.91
    .!
    0.91
     както
    0.89
    Activations Density 0.106%

    No Known Activations