© 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. 19993
    Prev
    Next
    INDEX
    Explanations

    possessive nouns

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

    The neuron detects possessive endings (apostrophe-s or plural apostrophe markers) in words.

    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
     how
    -1.52
     can
    -1.35
     neby
    -1.31
    ющему
    -1.29
    良いです
    -1.25
     sólo
    -1.25
    to
    -1.22
    𐀀
    -1.18
    
    -1.18
     potre
    -1.18
    POSITIVE LOGITS
    *{\
    1.69
     вона
    1.63
     cordones
    1.50
     dueños
    1.48
     discorso
    1.45
    śmy
    1.39
     cammino
    1.39
     agujeros
    1.38
     otros
    1.38
     ベクトル
    1.38
    Activations Density 0.055%

    No Known Activations