© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35039
    Prev
    Next
    INDEX
    Explanations

    FarmVille, Mario Brothers, sweet corn

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

    This neuron activates on distinctive proper names—especially brand, product, or trademark names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    tisseur
    -0.92
     Glied
    -0.91
    を行います
    -0.90
    日本的
    -0.87
    しっかり
    -0.87
    el
    -0.87
    ことができ
    -0.87
     moitié
    -0.86
     full
    -0.85
     picking
    -0.85
    POSITIVE LOGITS
     verhind
    1.16
     automóviles
    1.12
     automóvil
    1.08
    kredit
    1.07
    (),
    1.06
    ()/
    1.05
     vehículos
    1.04
     autres
    1.04
     menek
    1.03
     and
    1.02
    Activations Density 0.090%

    No Known Activations