© 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. 60150
    Prev
    Next
    INDEX
    Explanations

    courage

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

    The neuron strongly activates on the word “courage” (and its morphological variants like “courageous”), effectively detecting mentions of courage.

    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
    栳
    -3.47
    इटम
    -2.73
     pollici
    -2.64
     amores
    -2.59
    ﮕ
    -2.58
    ୈ
    -2.52
     年代
    -2.47
     perdagangan
    -2.42
    (*´
    -2.42
     governo
    -2.42
    POSITIVE LOGITS
    </td>
    2.83
    ↵↵↵↵
    2.67
    _{
    2.61
    </b>
    2.61
    ↵
    2.61
    ↵↵↵↵↵↵↵↵↵↵
    2.53
     of
    2.52
    怂
    2.52
    8
    2.48
     NEW
    2.47
    Activations Density 0.001%

    No Known Activations