© 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. 22-GEMMASCOPE-RES-131K
    7. 98559
    Prev
    Next
    INDEX
    Explanations

    parameter indices

    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_22/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
     all
    -1.03
     currently
    -0.92
    выя
    -0.90
    一面
    -0.88
     hoặc
    -0.87
     pneu
    -0.86
    ⼈
    -0.86
    意志
    -0.85
    雳
    -0.85
    fortnite
    -0.84
    POSITIVE LOGITS
     подойдет
    0.98
    那时候
    0.98
    で見る
    0.97
     saat
    0.97
    rah
    0.96
    笅
    0.94
     через
    0.94
    ָם
    0.92
     melalui
    0.90
    鋮
    0.90
    Activations Density 0.032%

    No Known Activations