© 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. 34-GEMMASCOPE-RES-131K
    7. 1150
    Prev
    Next
    INDEX
    Explanations

    main followed by a key component

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

    The neuron consistently activates on the word “main” (e.g. in “main circuit,” “main memory,” “main body,” etc.).

    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
    ctime
    -0.77
    ∑
    -0.75
    langer
    -0.73
     przeds
    -0.73
     mūsų
    -0.73
    řízení
    -0.72
    เก็บ
    -0.71
    thè
    -0.70
     Process
    -0.69
     erbjud
    -0.69
    POSITIVE LOGITS
    体的
    0.73
    യും
    0.73
     主
    0.73
    ORDAN
    0.73
     طف
    0.72
    罚
    0.72
    ત્
    0.72
     bonitas
    0.71
     passive
    0.71
    tainer
    0.71
    Activations Density 0.011%

    No Known Activations