© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 116608
    Prev
    Next
    INDEX
    Explanations

    foreign terms and 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_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
     garota
    -0.77
    省略
    -0.74
     convene
    -0.68
     stond
    -0.66
     Rhein
    -0.66
     Sachin
    -0.65
     Стан
    -0.65
     sorry
    -0.65
     состояние
    -0.65
    Raman
    -0.65
    POSITIVE LOGITS
     Gazetteer
    0.79
     Aik
    0.76
     cuck
    0.75
     extravagance
    0.74
    Brow
    0.72
     なん
    0.71
     sensei
    0.70
     consuls
    0.68
    thèse
    0.66
    ulex
    0.64
    Activations Density 0.063%

    No Known Activations