© 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. 22-GEMMASCOPE-RES-131K
    7. 35844
    Prev
    Next
    INDEX
    Explanations

    gender and marital status

    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_22/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
    oxidase
    -0.91
    ∧
    -0.88
    parseDouble
    -0.88
     duque
    -0.86
     administrador
    -0.84
     társ
    -0.83
     colectivo
    -0.82
    |+\
    -0.82
    Ong
    -0.81
    ğını
    -0.81
    POSITIVE LOGITS
     Vara
    0.89
    ler
    0.88
    月刊
    0.82
     tph
    0.82
     migh
    0.81
    umba
    0.81
     thym
    0.80
     lorem
    0.78
    Способ
    0.78
    ั้ง
    0.77
    Activations Density 0.001%

    No Known Activations