© 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. 119402
    Prev
    Next
    INDEX
    Explanations

    describing individuals and their traits

    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
     футболка
    -1.16
     speziellen
    -1.08
     スニーカー
    -1.06
     другими
    -0.91
     to
    -0.88
    обла
    -0.87
     Organisationen
    -0.87
    animity
    -0.87
    無人
    -0.86
    nasio
    -0.85
    POSITIVE LOGITS
     member
    1.57
     person
    1.48
     figure
    1.38
     guy
    1.30
     entity
    1.26
     presence
    1.23
     player
    1.20
     participant
    1.16
    presence
    1.13
     člove
    1.09
    Activations Density 0.067%

    No Known Activations