© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66299
    Prev
    Next
    INDEX
    Explanations

    words starting with v

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

    The neuron strongly activates on standalone “V” tokens and on any uppercase words or acronyms beginning with the letter V.

    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
     vinegar
    -1.20
     violin
    -1.14
    enedig
    -1.09
    黻
    -1.00
    疫苗
    -1.00
    uitton
    -0.97
     mueve
    -0.96
    酩
    -0.95
     faulty
    -0.94
     kaldı
    -0.94
    POSITIVE LOGITS
     Independ
    0.98
    棄
    0.97
     (...
    0.93
     (...)
    0.92
     cím
    0.89
    usic
    0.88
     Vz
    0.88
     Voy
    0.88
    quez
    0.86
    ‌ای
    0.86
    Activations Density 0.459%

    No Known Activations