© 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. 103253
    Prev
    Next
    INDEX
    Explanations

    incorporating revisions and feedback

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

    The neuron activates on the more informational, content-bearing tokens (e.g. key nouns, verbs, numbers, dates, and other non-stopword terms) rather than on common function words.

    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
    recently
    -0.98
     Petition
    -0.90
    lectable
    -0.89
     actuellement
    -0.88
    reibt
    -0.87
    年以上
    -0.86
     Proclamation
    -0.85
    Recently
    -0.84
     YEARS
    -0.84
    recent
    -0.83
    POSITIVE LOGITS
     revisions
    2.48
     modifications
    2.02
     corrections
    2.00
    修改
    1.89
     amendments
    1.80
     revision
    1.80
     revised
    1.78
     comments
    1.69
     edits
    1.66
     feedback
    1.64
    Activations Density 0.061%

    No Known Activations