© 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. 22-GEMMASCOPE-RES-131K
    4. 39833
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and 's'

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

    The neuron detects possessive constructions (genitives), i.e. words with "'s" or possessive pronouns like “our” and “his.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     allerlei
    -1.14
    🚀
    -1.09
    !」
    -1.09
     ambass
    -1.02
    tabIndex
    -1.01
    ✔️
    -1.00
     tille
    -1.00
    ſh
    -1.00
     historien
    -1.00
    pography
    -0.99
    POSITIVE LOGITS
     few
    1.73
     niewiel
    1.38
     group
    1.22
     recently
    1.22
     key
    1.16
     many
    1.14
     later
    1.10
     newer
    1.10
     early
    1.09
     nuestros
    1.09
    Activations Density 0.039%

    No Known Activations