© 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. 19180
    Prev
    Next
    INDEX
    Explanations

    interaction between entities

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

    The neuron specifically detects occurrences of the term “interaction” (especially in scientific and technical contexts).

    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
    哎呀
    -2.31
     avec
    -2.30
     ähnliche
    -2.22
    鉨
    -2.17
    カビ
    -2.16
    ین
    -2.14
    𓐍
    -2.11
    トマト
    -2.08
    Fø
    -2.06
     elevating
    -2.05
    POSITIVE LOGITS
    籐
    2.94
     For
    2.52
     What
    2.52
    ஂ
    2.45
     That
    2.45
     Then
    2.45
    訛
    2.42
    )...
    2.42
     When
    2.41
    ]
    2.39
    Activations Density 0.028%

    No Known Activations