© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69615
    Prev
    Next
    INDEX
    Explanations

    field activities and research

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

    The neuron fires on the word “field,” especially when it appears as part of technical collocations (e.g. “field isolates,” “field support,” “field experience,” etc.).

    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
    潺
    -1.28
    Liefs
    -1.15
    钣
    -1.13
    颯
    -1.12
    +}$
    -1.12
    ']['
    -1.11
    Sciences
    -1.10
    .}(
    -1.10
     anderen
    -1.10
    );
    
    -1.10
    POSITIVE LOGITS
     field
    1.74
     FIELD
    1.44
     is
    1.40
     fieldwork
    1.37
     Field
    1.32
    </strong>
    1.28
    Those
    1.22
     bleus
    1.16
     nových
    1.13
    Ainda
    1.12
    Activations Density 0.147%

    No Known Activations