© 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. 84418
    Prev
    Next
    INDEX
    Explanations

    modeling and models

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

    The neuron strongly activates on the word “model” (and its morphological variants like “models” or “modelling”).

    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
    狁
    -1.77
     unſ
    -1.76
     probabilmente
    -1.56
     فقط
    -1.52
    荭
    -1.50
    鹮
    -1.49
    
    -1.48
    葙
    -1.48
     hablaba
    -1.48
     eſſ
    -1.48
    POSITIVE LOGITS
     both
    2.02
    u
    1.73
     of
    1.66
    すれば
    1.61
     anche
    1.59
     if
    1.56
    ar
    1.52
     as
    1.51
     myös
    1.50
    O
    1.49
    Activations Density 0.065%

    No Known Activations