© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21341
    Prev
    Next
    INDEX
    Explanations

    mongoose models and schemas

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

    This neuron activates on occurrences of the identifier “model” (or “Model”) in code.

    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
     Ähnliche
    -1.51
    遏
    -1.41
     благодаря
    -1.41
     will
    -1.38
     Са
    -1.35
     wohin
    -1.33
    麾
    -1.30
    燎
    -1.29
    家主
    -1.29
    ’”
    -1.28
    POSITIVE LOGITS
     this
    1.65
     réalisés
    1.45
    盅
    1.30
     différents
    1.29
    </h4>
    1.29
    們
    1.28
    getRepository
    1.26
    錀
    1.23
    lancer
    1.21
    Dalam
    1.20
    Activations Density 0.008%

    No Known Activations