© 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. 7229
    Prev
    Next
    INDEX
    Explanations

    read minds

    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
    遑
    -0.91
    ı
    -0.88
     groen
    -0.85
    -0.83
    さみ
    -0.82
     دوربین
    -0.81
     Gruppo
    -0.79
    ≔
    -0.78
    事に
    -0.78
    ================
    -0.77
    POSITIVE LOGITS
     peoples
    4.63
     everyone
    3.09
     people
    2.94
     someone
    2.75
     everybody
    2.61
     somebody
    2.25
     Peoples
    2.16
    everyone
    2.14
    大家的
    2.11
    人们
    2.02
    Activations Density 0.262%
    No Known Activations