© 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. 85696
    Prev
    Next
    INDEX
    Explanations

    Coconut, Joy, or Harold

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

    The neuron activates on mentions of “coconut” (and its close variants, including the scientific name cocos nucifera).

    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
     it
    -1.91
    也會
    -1.71
    of
    -1.65
     verschiedenen
    -1.58
     carpenter
    -1.57
     поддержку
    -1.57
     bisschen
    -1.56
     خب
    -1.53
    al
    -1.52
     progression
    -1.51
    POSITIVE LOGITS
     estimés
    1.77
    Ꭳ
    1.72
    暂
    1.70
     issus
    1.64
    </td>
    1.63
     armée
    1.62
     piscina
    1.59
    ྃ
    1.58
    。
    1.56
    ”、“
    1.55
    Activations Density 0.011%

    No Known Activations