© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7367
    Prev
    Next
    INDEX
    Explanations

    surveys and customer feedback

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

    The neuron activates on mentions of surveys or questionnaire-style research (the word “survey” and its variants).

    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
    2
    -1.91
    7
    -1.62
     of
    -1.61
    ');
    -1.56
    }\
    -1.54
    在外
    -1.45
    1
    -1.43
     her
    -1.43
     budding
    -1.39
    5
    -1.38
    POSITIVE LOGITS
    ௅
    1.77
    閦
    1.76
     diventare
    1.66
    螃
    1.61
    蟊
    1.60
     pérd
    1.59
    ޏ
    1.56
     spus
    1.56
    刽
    1.50
    ことはありません
    1.49
    Activations Density 0.070%

    No Known Activations