© 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. 85862
    Prev
    Next
    INDEX
    Explanations

    preposition followed by noun

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

    The neuron fires strongly on the preposition “of” (and its close cognates in other languages, e.g. Danish af, om, ved, på).

    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
    5
    -1.62
    找个
    -1.49
    1
    -1.42
    事前に
    -1.41
     which
    -1.40
     comfortably
    -1.35
    0
    -1.33
     only
    -1.30
    今後も
    -1.30
    我这
    -1.29
    POSITIVE LOGITS
    })$
    1.48
    phim
    1.42
    cartier
    1.38
    endforeach
    1.38
     cristales
    1.37
     régi
    1.35
     konkrete
    1.34
     espejos
    1.34
    blins
    1.34
     Vainqueur
    1.33
    Activations Density 0.207%

    No Known Activations