© 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. 59802
    Prev
    Next
    INDEX
    Explanations

    mongoose queries, MRP, POR, Rout

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

    The neuron activates on occurrences of the identifier “mongoose,” i.e. mentions of the Mongoose library in code or queries.

    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
    ↵↵
    -3.13
    ’
    -3.13
    </b>
    -2.86
            
    -2.66
    ,’
    -2.63
         
    -2.58
    ');
    -2.56
     .
    -2.53
    ,’”
    -2.50
      
    -2.45
    POSITIVE LOGITS
     maniere
    2.84
    硨
    2.73
    嗵
    2.69
    撘
    2.69
     ventre
    2.69
     murale
    2.66
    ᕱ
    2.66
    錞
    2.63
    Ꮵ
    2.63
     tradis
    2.61
    Activations Density 0.028%

    No Known Activations