© 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. 58761
    Prev
    Next
    INDEX
    Explanations

    guy-girl relationships

    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
    everyone
    -0.98
     Năm
    -0.96
     Khart
    -0.93
     INSTR
    -0.93
     schoolchildren
    -0.91
    ଓ
    -0.91
     grâce
    -0.90
     châssis
    -0.90
    people
    -0.88
     voyager
    -0.88
    POSITIVE LOGITS
     his
    1.66
     guy
    1.59
     girl
    1.44
     your
    1.40
     woman
    1.34
     guys
    1.29
     women
    1.27
     muž
    1.23
     showing
    1.23
     you
    1.20
    Activations Density 0.028%

    No Known Activations