© 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. 10-GEMMASCOPE-RES-131K
    7. 87138
    Prev
    Next
    INDEX
    Explanations

    origin or delivery

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

    The neuron is specifically detecting the preposition “of,” especially in formal or title‐style 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
     ihrem
    -1.23
    meld
    -1.23
    UNTIME
    -1.21
     potentiel
    -1.20
     maestra
    -1.20
     giallo
    -1.19
    呿
    -1.19
    芣
    -1.18
    unno
    -1.18
     cerve
    -1.18
    POSITIVE LOGITS
     your
    1.53
     use
    1.38
     or
    1.32
     after
    1.27
     each
    1.24
     if
    1.23
     at
    1.21
     specific
    1.21
     those
    1.21
     speciality
    1.20
    Activations Density 0.271%

    No Known Activations