© 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. 22-GEMMASCOPE-RES-131K
    7. 9490
    Prev
    Next
    INDEX
    Explanations

    too [adjective] context

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

    The neuron fires on descriptive adjectives that convey magnitude or intensity (e.g. small, big, bright, high, restrictive, specific).

    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
    えっ
    -1.89
    あー
    -1.59
    ごめん
    -1.41
    久し
    -1.40
    あぁ
    -1.38
    すっ
    -1.35
    ところに
    -1.32
    つづく
    -1.31
    ええ
    -1.30
    で見る
    -1.30
    POSITIVE LOGITS
     to
    2.48
     for
    1.92
     or
    1.58
    <bos>
    1.57
     now
    1.46
     of
    1.38
     on
    1.37
     in
    1.37
     than
    1.37
     then
    1.35
    Activations Density 0.018%

    No Known Activations