© 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. 104099
    Prev
    Next
    INDEX
    Explanations

    mortgage, mortuary, mortality, mortally

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

    The neuron activates on any word beginning with the root “mort” (e.g. mortuary, mortgage, mortality).

    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
     resounding
    -2.55
     envelop
    -2.45
    太好了
    -2.42
     sorta
    -2.31
     Ciebie
    -2.30
     ними
    -2.30
    _
    -2.28
    以上です
    -2.23
    
    -2.22
     на
    -2.17
    POSITIVE LOGITS
    𞤢
    2.77
    鋨
    2.75
    ㉗
    2.45
    脔
    2.39
    they
    2.38
    Y
    2.38
    ⃚
    2.33
     поддержа
    2.31
    鹪
    2.31
    𔘓
    2.30
    Activations Density 0.005%

    No Known Activations