© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 100171
    Prev
    Next
    INDEX
    Explanations

    surname Foster

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

    The neuron selectively activates on the surname “Foster.”

    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
    猡
    -2.75
    璈
    -2.53
    ſſel
    -2.38
    
    -2.36
    据说
    -2.36
    瘿
    -2.34
     красивые
    -2.34
    Ⲉ
    -2.33
    鑁
    -2.33
    倌
    -2.31
    POSITIVE LOGITS
    It
    3.55
    {
    2.95
    If
    2.92
    >
    2.83
    When
    2.77
    o
    2.70
     Then
    2.66
    a
    2.64
    ных
    2.61
    While
    2.55
    Activations Density 0.002%

    No Known Activations