© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129199
    Prev
    Next
    INDEX
    Explanations

    provide or receive aid

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

    The neuron strongly activates on the substring “aided,” i.e. words ending with “aided” (e.g. computer-aided, auxiliary-aided).

    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
     enormous
    -2.86
     exquisite
    -2.86
     exquisitely
    -2.81
     impeccable
    -2.81
     oddly
    -2.75
     extraordinarily
    -2.75
     intricate
    -2.70
     or
    -2.67
     impressive
    -2.64
    ”
    -2.64
    POSITIVE LOGITS
    genodigd
    2.88
    缯
    2.86
    訁
    2.81
     Não
    2.72
    泐
    2.66
     soooo
    2.64
    出来て
    2.63
    鹇
    2.56
    鋱
    2.56
     lauded
    2.56
    Activations Density 0.003%

    No Known Activations