© 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. 107554
    Prev
    Next
    INDEX
    Explanations

    ibn, bin, mac (son of)

    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
    」　
    -0.88
     عملیات
    -0.85
    。)
    -0.82
    キャンセル
    -0.81
     suicidio
    -0.80
    と思ったら
    -0.79
    Productos
    -0.79
    על
    -0.76
    intele
    -0.75
     jouets
    -0.75
    POSITIVE LOGITS
    ためには
    0.94
     ぱ
    0.93
    )=>{
    0.90
    setFile
    0.88
    aéroport
    0.87
    ♝
    0.86
    訕
    0.85
     antwoord
    0.85
     tersebut
    0.84
     confluence
    0.84
    Activations Density 0.006%

    No Known Activations