© 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. 74963
    Prev
    Next
    INDEX
    Explanations

    distress and related words

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

    The main thing this neuron does is detect the word “distress.”

    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
    糨
    -2.84
    跩
    -2.45
     Некоторые
    -2.30
     Многие
    -2.30
    臏
    -2.27
    enablog
    -2.25
     včetně
    -2.25
     唯美
    -2.25
    肪
    -2.23
     envisioned
    -2.22
    POSITIVE LOGITS
    ↵↵
    3.16
    ’
    3.03
    ↵
    3.02
    “
    2.66
    s
    2.53
    ),
    2.44
    ",
    2.38
    .
    2.22
    \
    2.14
    ского
    2.13
    Activations Density 0.004%

    No Known Activations