© 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. 90431
    Prev
    Next
    INDEX
    Explanations

    wellbeing and Newtown

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

    The neuron flags occurrences of the term “wellbeing” (or “well-being”) in the text.

    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
    \
    -2.91
    0
    -2.48
    },
    -2.47
    鞮
    -2.31
    しっかり
    -2.30
     essere
    -2.30
    к
    -2.28
    ar
    -2.17
     entsprechende
    -2.16
    "
    -2.16
    POSITIVE LOGITS
    n
    2.56
    媄
    2.22
    Ꭳ
    2.22
    ization
    2.16
    作为一个
    2.13
    当你
    2.11
    鹛
    2.09
    ྅
    2.09
     土産
    2.02
    面接
    2.02
    Activations Density 0.001%

    No Known Activations