© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13496
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by aspects

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

    The neuron specifically detects the second‐person possessive pronoun “your.”

    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
     maksi
    -1.97
     vokal
    -1.77
     seksi
    -1.77
     meil
    -1.75
     raha
    -1.71
    
    -1.67
     osal
    -1.67
     taha
    -1.63
     alha
    -1.63
     laad
    -1.61
    POSITIVE LOGITS
     also
    1.86
    In
    1.56
     eyes
    1.53
     or
    1.48
     sapore
    1.46
     own
    1.41
     uses
    1.41
    ueves
    1.37
    日程
    1.36
    ",
    1.33
    Activations Density 0.064%

    No Known Activations