© 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. 415
    Prev
    Next
    INDEX
    Explanations

    Dear salutations

    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
    Удачи
    -0.81
    pédie
    -0.77
    typeorm
    -0.75
     شهید
    -0.73
    mo
    -0.72
    話し
    -0.71
    werfer
    -0.71
     اختلال
    -0.71
    EndOf
    -0.70
    Приятного
    -0.70
    POSITIVE LOGITS
    Dear
    6.13
     Dear
    5.88
     dear
    5.81
    dear
    4.28
     DEAR
    3.80
     dearest
    3.55
    DEAR
    3.27
    Dearest
    2.58
    亲爱的
    2.48
     dearly
    2.45
    Activations Density 0.122%

    No Known Activations