© 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. 115441
    Prev
    Next
    INDEX
    Explanations

    se... should do

    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
    être
    -1.20
    şık
    -0.98
     être
    -0.96
     sido
    -0.93
     mít
    -0.88
    리를
    -0.87
     být
    -0.87
    ของ
    -0.86
    нений
    -0.86
     была
    -0.84
    POSITIVE LOGITS
     proceed
    1.06
     can
    1.05
    んですよ
    1.03
    Может
    0.93
    Недо
    0.91
     gebeurt
    0.91
    んですよね
    0.90
    Переваги
    0.90
    大丈夫です
    0.89
    ibouti
    0.88
    Activations Density 0.003%

    No Known Activations