© 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. 34-GEMMASCOPE-RES-131K
    7. 93330
    Prev
    Next
    INDEX
    Explanations

    invention and introduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ebly
    -0.80
    IDX
    -0.79
    ceiro
    -0.77
     lascia
    -0.77
     piatta
    -0.77
    暉
    -0.75
     bygga
    -0.74
     untrained
    -0.73
     sélectionné
    -0.73
    陕西
    -0.73
    POSITIVE LOGITS
     invented
    4.94
     invention
    4.09
     invent
    3.83
    vented
    3.33
     inventing
    3.16
     придума
    3.11
    invent
    3.05
    invention
    2.94
    Invent
    2.91
     изобре
    2.88
    Activations Density 0.149%

    No Known Activations