© 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. 70082
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron fires on proper names, especially personal names and surnames.

    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
     in
    -2.02
     you
    -1.77
     In
    -1.47
     your
    -1.45
    You
    -1.40
    collegiate
    -1.39
     Komunikasi
    -1.39
    detek
    -1.38
     for
    -1.37
    錚
    -1.34
    POSITIVE LOGITS
    ⽼
    1.48
    儅
    1.42
     продолжает
    1.41
    2
    1.41
    mbres
    1.39
    相同的
    1.38
     zui
    1.35
     leone
    1.31
     厂家
    1.31
    ांत
    1.30
    Activations Density 0.183%

    No Known Activations