© 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. 34-GEMMASCOPE-RES-131K
    7. 99474
    Prev
    Next
    INDEX
    Explanations

    assisted living, reproduction, or death

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

    the term "assisted" in healthcare or reproductive contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron strongly activates on the word “assisted” (e.g. in “assisted living,” “assisted suicide,” “assisted reproduction,” 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_34/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
    turning
    -0.70
     terbesar
    -0.63
    rukt
    -0.63
    mest
    -0.63
     Connecting
    -0.63
     Küche
    -0.62
     prochaines
    -0.62
    вел
    -0.62
     greet
    -0.61
    рили
    -0.61
    POSITIVE LOGITS
    LayoutStyle
    0.71
     чи
    0.71
    жи
    0.70
     Slab
    0.70
     Mato
    0.68
     Wigan
    0.68
     sulf
    0.67
    GetString
    0.67
     Romano
    0.66
     Manas
    0.66
    Activations Density 0.084%

    No Known Activations