© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16171
    Prev
    Next
    INDEX
    Explanations

    default followed by Dataset or Class or Block or References or Settings or Games or Login or Behavior or Logs or Upgrade

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

    The neuron fires on standalone identifier-style tokens used as field or parameter names (e.g. “default,” “Last,” “Min,” “Max,” “Attached,” etc.) in configuration, metadata, or schema files.

    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
    などを
    -2.13
    などが
    -2.02
    を
    -1.95
    などは
    -1.78
    や
    -1.66
    が
    -1.61
    では
    -1.56
    でも
    -1.55
    なども
    -1.55
     alcune
    -1.52
    POSITIVE LOGITS
    為に
    1.59
    んですよね
    1.52
    づくり
    1.50
    総評
    1.48
    ところに
    1.48
    にほんブログ村
    1.48
    ほうがいい
    1.44
    方がいい
    1.43
    んだろう
    1.41
    を選択します
    1.38
    Activations Density 0.027%

    No Known Activations