© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113891
    Prev
    Next
    INDEX
    Explanations

    Fukushima nuclear, Tsurumi, Irexit, 富商

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

    The neuron responds to occurrences of the name “Fukushima.”

    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
    ...."
    -2.67
     tantas
    -2.59
    -...
    -2.48
    很棒
    -2.44
     puertos
    -2.44
     poderosos
    -2.41
    ⎆
    -2.41
     (...)
    -2.41
     aceites
    -2.39
    他自己
    -2.34
    POSITIVE LOGITS
    .
    3.58
    2
    3.28
    {
    2.67
     Which
    2.56
    T
    2.53
     Because
    2.48
     &
    2.47
    _
    2.41
    ya
    2.39
            
    2.33
    Activations Density 0.002%

    No Known Activations