© 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. 98138
    Prev
    Next
    INDEX
    Explanations

    possessive determiners before nouns

    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_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
     tumor
    -0.99
     flavorful
    -0.97
     еще
    -0.97
     ее
    -0.96
     coworkers
    -0.96
     counseling
    -0.94
     cantidad
    -0.94
     enrol
    -0.94
     neighborhoods
    -0.93
     organized
    -0.91
    POSITIVE LOGITS
     wider
    1.09
     onward
    0.96
     remit
    0.92
     nearest
    0.91
    ű
    0.88
     undoubted
    0.85
     timescale
    0.85
     specialist
    0.85
    nearest
    0.84
    wider
    0.84
    Activations Density 0.067%

    No Known Activations