© 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. 109473
    Prev
    Next
    INDEX
    Explanations

    whose clause and possessives

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

    This neuron spotlights the central content word—typically a key noun or technical term that denotes the main subject of the sentence.

    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
     jaką
    -1.04
    の種類
    -1.01
    お待ちしております
    -0.93
    性を
    -0.90
    的要求
    -0.84
    の紹介
    -0.84
    她也
    -0.84
    iddharth
    -0.83
     इसे
    -0.82
     jakie
    -0.81
    POSITIVE LOGITS
     whose
    8.31
    whose
    6.56
     Whose
    5.41
    Whose
    5.41
     cuyo
    4.50
     cuya
    4.47
     cuyos
    4.09
     cuyas
    3.84
     cuja
    3.58
     cujo
    3.52
    Activations Density 0.296%

    No Known Activations