© 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. 10-GEMMASCOPE-RES-131K
    4. 12385
    Prev
    Next
    INDEX
    Explanations

    coming or arriving

    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_10/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
    鹇
    -2.09
    凩
    -1.92
    uſe
    -1.87
    _
    -1.82
     レトロ
    -1.80
     truk
    -1.78
     rispondere
    -1.75
     первой
    -1.74
    
    -1.73
     buscando
    -1.73
    POSITIVE LOGITS
     Perhaps
    1.70
     Only
    1.66
    ↵↵
    1.66
    ydı
    1.58
     Even
    1.56
    兩個
    1.54
     Also
    1.53
    知る
    1.51
    ).
    1.51
    ene
    1.48
    Activations Density 0.004%

    No Known Activations