© 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. 39306
    Prev
    Next
    INDEX
    Explanations

    fields

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

    The neuron fires on occurrences of the word “field” (especially its plural form “fields”).

    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
    瘣
    -2.44
    的过程中
    -2.44
     脸
    -2.42
    许久
    -2.38
    檄
    -2.36
    ן
    -2.36
    ed
    -2.36
    </h2>
    -2.31
    윔
    -2.30
    ！！！”
    -2.27
    POSITIVE LOGITS
     If
    3.36
    If
    2.69
    There
    2.66
     namun
    2.61
    可以
    2.48
    нутрен
    2.44
     But
    2.38
    When
    2.31
    ]
    2.28
    炝
    2.28
    Activations Density 0.008%

    No Known Activations