© 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. 34-GEMMASCOPE-RES-131K
    7. 63779
    Prev
    Next
    INDEX
    Explanations

    Ben followed by another word

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

    The neuron fires on occurrences of the sub‐token “Ben” (the capitalized “Ben” prefix in names or words).

    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
    を
    -0.69
    тей
    -0.68
     giudice
    -0.66
     single
    -0.66
    各
    -0.65
    single
    -0.65
    但却
    -0.65
    粗
    -0.65
     РФ
    -0.64
     einzelne
    -0.64
    POSITIVE LOGITS
    Ben
    1.16
     BEN
    1.01
     Ben
    0.95
     ben
    0.93
    BEN
    0.91
     Venue
    0.90
     kategorii
    0.89
    tham
    0.89
     problemen
    0.86
    ルム
    0.85
    Activations Density 0.011%

    No Known Activations