© 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. 82905
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun followed by noun

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

    The neuron fires on words immediately adjacent to inline numeric citations or reference markers.

    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
    Roads
    -1.11
     új
    -1.08
     tudom
    -1.02
     スイーツ
    -1.02
     réus
    -0.99
     změ
    -0.97
    "]));
    -0.95
    Ida
    -0.95
     zmian
    -0.93
    Aç
    -0.93
    POSITIVE LOGITS
     existing
    1.95
     way
    1.90
     already
    1.74
     definition
    1.60
     approach
    1.60
     wording
    1.55
     bestaande
    1.54
     format
    1.51
     parameters
    1.45
     layout
    1.42
    Activations Density 0.076%

    No Known Activations