© 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. 7232
    Prev
    Next
    INDEX
    Explanations

    accented characters and compose

    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
     nhiêu
    -0.71
    ً
    -0.70
     WAR
    -0.69
     dobra
    -0.69
    WAR
    -0.68
     inform
    -0.68
    ńskiego
    -0.68
    fdb
    -0.67
     mismanagement
    -0.67
    Ive
    -0.67
    POSITIVE LOGITS
     acute
    1.05
     Compose
    0.96
     accents
    0.93
     accented
    0.89
    Compose
    0.87
     accent
    0.83
    accent
    0.83
     accentuated
    0.82
     compose
    0.80
    compose
    0.78
    Activations Density 0.099%

    No Known Activations