© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118408
    Prev
    Next
    INDEX
    Explanations

    Benoit Blanc's name and context

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

    The neuron is particularly sensitive to tokens written in uppercase or title-case (e.g. proper names, tag names, comment delimiters).

    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
    uploader
    -0.80
     surreal
    -0.77
     vídeo
    -0.75
    mtrl
    -0.74
     Padang
    -0.73
     piccolo
    -0.73
    Penalty
    -0.73
    ligg
    -0.73
     penalty
    -0.71
    <0x9D>
    -0.71
    POSITIVE LOGITS
     Knives
    1.27
    Kni
    1.14
     Benoit
    1.05
     knives
    0.93
    Blanc
    0.89
     Blanc
    0.88
     Throm
    0.86
     johnson
    0.77
     Johnson
    0.75
     Andi
    0.73
    Activations Density 0.019%

    No Known Activations