© 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. 22-GEMMASCOPE-RES-131K
    7. 25246
    Prev
    Next
    INDEX
    Explanations

    used as an alternative

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

    The neuron consistently fires on occurrences of the word “as.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    Итог
    -1.06
    зыв
    -0.94
    taña
    -0.93
    oncé
    -0.93
    Ona
    -0.88
     зависит
    -0.88
    ibid
    -0.87
    goyle
    -0.87
     pelear
    -0.87
     nová
    -0.86
    POSITIVE LOGITS
     instead
    2.50
     вместо
    2.00
     zamiast
    1.86
    instead
    1.55
    Instead
    1.48
    作为
    1.41
     Instead
    1.34
     invece
    1.27
     replacing
    1.23
     качестве
    1.21
    Activations Density 0.141%

    No Known Activations