© 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. 42269
    Prev
    Next
    INDEX
    Explanations

    mantle, mantel, or Manteca

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

    The neuron strongly activates on the word “mantle” (including spelling variants like “mantel”), regardless of context.

    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
    翾
    -2.70
     Tatsache
    -2.39
     unangemess
    -2.33
    ⸰
    -2.23
    甞
    -2.22
     Which
    -2.17
    鬭
    -2.17
     angene
    -2.16
     ainfi
    -2.05
    疍
    -2.05
    POSITIVE LOGITS
    </h2>
    2.86
    汌
    2.45
    及び
    2.31
    邂
    2.31
    徊
    2.31
     seem
    2.30
    是非常
    2.23
    </sup>
    2.23
    <td>
    2.20
    й
    2.17
    Activations Density 0.002%

    No Known Activations