© 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. 10-GEMMASCOPE-RES-131K
    7. 60635
    Prev
    Next
    INDEX
    Explanations

    Intel Corporation

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

    The neuron fires on occurrences of the company name “Intel.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵
    -4.06
     
    -2.55
     Their
    -2.47
    要有
    -2.36
    差别
    -2.23
     realizando
    -2.16
    自然的
    -2.16
    ’
    -2.14
     secos
    -2.14
     These
    -2.13
    POSITIVE LOGITS
    there
    2.95
     từ
    2.64
     ở
    2.61
     在
    2.61
    倻
    2.59
    珦
    2.56
    Ꮌ
    2.56
    ቧ
    2.55
    ﻒ
    2.48
    ſſen
    2.44
    Activations Density 0.005%

    No Known Activations