© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72821
    Prev
    Next
    INDEX
    Explanations

    living with conditions or disabilities

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

    The neuron strongly activates on the preposition “with” when it introduces a medical condition or chronic illness (e.g. “living with arthritis,” “people living with HIV,” 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
    '
    -1.63
    lusconi
    -1.45
    饽
    -1.42
            
    -1.39
     If
    -1.38
     into
    -1.38
    сей
    -1.38
     Another
    -1.36
    чів
    -1.36
    いい
    -1.35
    POSITIVE LOGITS
    with
    1.70
     repercussions
    1.65
    或
    1.62
    にほんブログ村
    1.59
    itado
    1.58
     puntas
    1.54
     TAMBIÉN
    1.54
     tranſ
    1.52
    también
    1.52
    Namun
    1.52
    Activations Density 0.010%

    No Known Activations