© 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. 92427
    Prev
    Next
    INDEX
    Explanations

    special words and phrases

    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
    蠟
    -0.84
    GetAll
    -0.81
     inductor
    -0.77
    マネ
    -0.74
    قع
    -0.74
     Pläne
    -0.74
     quizás
    -0.73
     metastatic
    -0.72
    試合
    -0.72
     地图
    -0.71
    POSITIVE LOGITS
    Ữ
    0.82
    үү
    0.79
    criterion
    0.78
    
    0.78
    province
    0.77
    atle
    0.76
    ᴸ
    0.75
    ље
    0.74
    Axios
    0.73
     pourquoi
    0.73
    Activations Density 0.000%

    No Known Activations