© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45190
    Prev
    Next
    INDEX
    Explanations

    preposition followed by proper nouns

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

    This neuron fires on the German preposition “von” (including its contracted form “vom”) when marking names or genitive phrases.

    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
     \
    -2.44
    .”
    -2.33
    this
    -1.96
     ―
    -1.90
    ]."
    -1.89
    ",
    -1.85
    ?"
    -1.84
    𓆜
    -1.78
     they
    -1.78
    after
    -1.77
    POSITIVE LOGITS
     niemand
    2.22
     them
    2.14
    спомина
    2.11
     żołnier
    2.00
    摭
    1.98
     afar
    1.98
     октя
    1.97
     dziew
    1.94
     inmiddels
    1.92
    えっ
    1.85
    Activations Density 0.006%

    No Known Activations