© 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. 118405
    Prev
    Next
    INDEX
    Explanations

    of mine, of ours, of hers

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

    This neuron detects noun phrases in the “X of mine” possessive construction.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     theirs
    -2.73
    irs
    -1.97
     THEIR
    -1.69
     their
    -1.59
    their
    -1.33
     Their
    -1.30
    Their
    -1.27
     our
    -1.20
     your
    -1.15
     их
    -1.13
    POSITIVE LOGITS
     hers
    1.41
     mine
    1.11
    Hers
    1.05
     Hers
    0.92
    İZ
    0.79
     mines
    0.78
     myself
    0.73
     fia
    0.73
    urare
    0.69
     mind
    0.68
    Activations Density 0.010%

    No Known Activations