© 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. 41440
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns across languages

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron activates most strongly on the single keyword in a paper or patent title/abstract that names its central subject or focus.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     groen
    -1.43
     adu
    -1.43
    側の
    -1.41
    ssss
    -1.38
    the
    -1.34
     expo
    -1.26
    sssss
    -1.25
    两只
    -1.25
    趵
    -1.23
    izaron
    -1.22
    POSITIVE LOGITS
     their
    1.93
     Mereka
    1.80
     których
    1.73
     Their
    1.64
     jejich
    1.63
     รวม
    1.49
     themselves
    1.49
     leur
    1.48
     обычно
    1.48
    Their
    1.45
    Activations Density 0.534%

    No Known Activations