© 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. 130387
    Prev
    Next
    INDEX
    Explanations

    "the" followed by specific words

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

    The neuron is strongly activated by the prepositional “of” when it appears in noun‐phrase or technical‐style constructions.

    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
     of
    -2.23
     bidra
    -1.45
     boya
    -1.45
     himo
    -1.44
     kuno
    -1.43
     kampen
    -1.38
     lanka
    -1.37
    BOTH
    -1.37
    ᠬ
    -1.36
     huset
    -1.35
    POSITIVE LOGITS
     some
    1.62
     a
    1.54
     many
    1.36
     gutes
    1.19
     tends
    1.18
     from
    1.18
    Soporte
    1.16
    Tá
    1.15
     for
    1.14
     an
    1.13
    Activations Density 0.101%

    No Known Activations