© 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. 54089
    Prev
    Next
    INDEX
    Explanations

    Ay prefix and standalone

    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
     Previously
    -0.86
     வே
    -0.78
    tricos
    -0.73
    途中で
    -0.71
     merasakan
    -0.71
     warns
    -0.71
    ensation
    -0.69
    INCLUDING
    -0.69
    addImage
    -0.69
     aggiungere
    -0.69
    POSITIVE LOGITS
    Ay
    0.93
    meric
    0.88
     Ay
    0.87
     AY
    0.81
     skoro
    0.80
    recognition
    0.78
    Ai
    0.77
     rejection
    0.75
     Rejection
    0.75
    アイ
    0.73
    Activations Density 0.014%

    No Known Activations