© 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. 87148
    Prev
    Next
    INDEX
    Explanations

    pairs and couples

    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
    一人で
    -0.94
     pensamento
    -0.83
    न्ध
    -0.82
    にいる
    -0.81
    prins
    -0.80
    だけでは
    -0.78
    ビックリ
    -0.76
    みんなで
    -0.74
     proveedor
    -0.74
    令人
    -0.73
    POSITIVE LOGITS
     occupancy
    0.91
     or
    0.84
     acrylic
    0.82
     domác
    0.79
    bedded
    0.79
     format
    0.78
    作業
    0.77
     hjälpa
    0.77
    ведь
    0.77
    时光
    0.76
    Activations Density 0.045%

    No Known Activations