© 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. 82856
    Prev
    Next
    INDEX
    Explanations

    husband and wife 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
    对他
    -1.13
     сама
    -0.93
     herself
    -0.88
    dding
    -0.87
     spokeswoman
    -0.86
     giggled
    -0.83
    té
    -0.83
     मिन
    -0.79
    туре
    -0.79
     him
    -0.79
    POSITIVE LOGITS
     himself
    1.54
     she
    1.51
     ей
    1.34
    娶
    1.20
     proposal
    1.19
     masculinity
    1.17
     sperm
    1.16
     ją
    1.13
     her
    1.12
     она
    1.10
    Activations Density 0.069%

    No Known Activations