© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47487
    Prev
    Next
    INDEX
    Explanations

    described by prepositions

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

    The neuron strongly activates on common relational function words (especially prepositions and linking adverbs) such as “in,” “by,” “also,” “present,” “mediated,” and “into.”

    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
     that
    -1.70
     this
    -1.52
     there
    -1.36
     thats
    -1.32
     like
    -1.28
     такую
    -1.27
     hierfür
    -1.20
     molta
    -1.20
     about
    -1.18
     đó
    -1.17
    POSITIVE LOGITS
     our
    1.48
     czerwca
    1.43
    Ngoài
    1.42
     марта
    1.35
    Porque
    1.34
    后来
    1.32
     TAMBÉM
    1.32
     then
    1.32
     شامل
    1.32
    Pokud
    1.31
    Activations Density 0.268%

    No Known Activations