© 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. 54090
    Prev
    Next
    INDEX
    Explanations

    word prefixes and suffixes

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

    The neuron detects short (two‐ or three‐letter) capitalized letter sequences at the start of proper names or acronyms.

    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
    を
    -1.91
    動機
    -1.80
    が
    -1.76
    そして
    -1.53
    立場
    -1.46
    暇
    -1.42
     in
    -1.40
    參考文獻
    -1.39
    <bos>
    -1.38
    外部連結
    -1.37
    POSITIVE LOGITS
    為に
    2.34
    必要がある
    1.97
    たびに
    1.84
    に入れる
    1.75
    になってしまう
    1.70
    で見る
    1.65
    際には
    1.64
    のではなく
    1.64
    事が
    1.62
    際は
    1.61
    Activations Density 0.142%

    No Known Activations