© 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. 83982
    Prev
    Next
    INDEX
    Explanations

    rearranging data for organization

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

    The neuron activates strongly on words related to sorting or sifting processes (e.g. “sorting,” “sifting,” “screening”).

    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
     same
    -2.09
    .
    -2.03
     einzigen
    -1.73
     berühmten
    -1.71
     Sadly
    -1.68
    $
    -1.61
     to
    -1.58
     {
    -1.50
     Perhaps
    -1.49
     Surprisingly
    -1.48
    POSITIVE LOGITS
     futurs
    1.80
     demostr
    1.70
     proactively
    1.69
    thumbsup
    1.63
     eſt
    1.63
    
    1.62
    
    1.61
     ſay
    1.55
    哢
    1.55
     ſa
    1.55
    Activations Density 0.032%

    No Known Activations