© 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. 115993
    Prev
    Next
    INDEX
    Explanations

    group and collective

    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
     بک
    -0.77
     HAM
    -0.73
    ükü
    -0.72
    瞌
    -0.72
    グロ
    -0.72
     lunches
    -0.71
    人员
    -0.71
    ุ่น
    -0.71
     kha
    -0.70
    <0xB8>
    -0.70
    POSITIVE LOGITS
     collective
    4.31
    collective
    3.61
     group
    3.48
    Collective
    2.98
     Collective
    2.94
     collectif
    2.91
     communal
    2.81
     collectively
    2.80
    group
    2.56
     коллек
    2.56
    Activations Density 0.107%

    No Known Activations