© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81548
    Prev
    Next
    INDEX
    Explanations

    purchase, lend, commits

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

    The neuron specializes in spotting capitalized proper names or titled phrases (e.g. “Reverse Lend-Lease”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     năm
    -0.81
     melhores
    -0.79
    Back
    -0.70
    ின்
    -0.69
    ctober
    -0.67
    heb
    -0.67
     hacia
    -0.64
    zib
    -0.64
     годах
    -0.64
     Back
    -0.63
    POSITIVE LOGITS
    шити
    0.79
    triggers
    0.69
    ationen
    0.68
     Denna
    0.67
    Kör
    0.67
     ノ
    0.66
    revision
    0.65
     Dupont
    0.64
    ollectionView
    0.64
     karakter
    0.64
    Activations Density 0.067%

    No Known Activations