© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 643
    Prev
    Next
    INDEX
    Explanations

    Japanese verbs and suffixes

    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
    Их
    -0.82
    et
    -0.78
     vya
    -0.75
    
    -0.75
     aswell
    -0.74
    睞
    -0.74
     vux
    -0.72
     やすい
    -0.72
    參考文獻
    -0.71
    رارة
    -0.70
    POSITIVE LOGITS
    MatButtonModule
    0.86
    nagy
    0.85
    universo
    0.82
    cedula
    0.82
     SDG
    0.81
    MatIconModule
    0.81
    zzard
    0.80
    ḿ
    0.80
    vacy
    0.80
    abord
    0.79
    Activations Density 0.002%

    No Known Activations