© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105025
    Prev
    Next
    INDEX
    Explanations

    male pronouns describing actions

    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_10/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
     herself
    -2.44
    athed
    -1.66
    pherds
    -1.52
    dding
    -1.46
     positivas
    -1.43
    esh
    -1.41
     personalizada
    -1.41
     of
    -1.40
    mme
    -1.38
     dinosaurio
    -1.37
    POSITIVE LOGITS
     himself
    3.20
     نفسه
    2.00
     mücade
    1.62
     tartış
    1.52
    himself
    1.50
     "",
    1.45
     accordance
    1.43
    หน้านี้
    1.43
     to
    1.41
    حياته
    1.40
    Activations Density 0.510%

    No Known Activations