© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45341
    Prev
    Next
    INDEX
    Explanations

    susceptible to

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

    The neuron detects the word "susceptible" and its context, typically when discussing vulnerability to diseases, conditions, or environmental factors.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    嵙
    -2.73
    翃
    -2.69
    琑
    -2.61
    苾
    -2.39
    魉
    -2.38
    頃の
    -2.22
    擄
    -2.20
    UAWEI
    -2.20
     ‘
    -2.20
    欒
    -2.19
    POSITIVE LOGITS
    ↵
    3.45
    \
    3.22
    ஂ
    2.61
    ൎ
    2.42
    ୌ
    2.38
     That
    2.30
    quirrel
    2.28
    昻
    2.25
    șit
    2.25
    bieron
    2.20
    Activations Density 0.010%

    No Known Activations