© 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. 35452
    Prev
    Next
    INDEX
    Explanations

    tech company actions

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

    The neuron is selectively activated by mentions of tech company or product brand 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
     or
    -1.97
     that
    -1.60
     our
    -1.42
     atau
    -1.29
    。“
    -1.20
    кість
    -1.20
    {~
    -1.20
    ！"
    -1.16
     oraz
    -1.15
     diskusi
    -1.15
    POSITIVE LOGITS
     resolução
    1.56
     seção
    1.39
     cópia
    1.30
     PREFACE
    1.28
     Washable
    1.27
    もありました
    1.25
    茈
    1.25
    だったが
    1.23
     môžete
    1.21
    basically
    1.21
    Activations Density 0.054%

    No Known Activations