© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14357
    Prev
    Next
    INDEX
    Explanations

    cryptography key generation

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

    The neuron detects multi-digit numeric tokens (i.e. literal numbers of three or more digits).

    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
    はコチラ
    -2.44
    のご紹介
    -2.13
    に行って
    -2.09
    の詳細
    -1.95
    をチェック
    -1.94
     and
    -1.93
    はこんな感じ
    -1.88
    をご覧
    -1.87
    為に
    -1.84
    {
    -1.84
    POSITIVE LOGITS
    UCIÓN
    1.83
    もある
    1.82
    <bos>
    1.80
    薔薇
    1.80
    螣
    1.75
    曖昧さ回避
    1.73
    風景
    1.73
    Поэтому
    1.71
    linawan
    1.71
    nitř
    1.70
    Activations Density 0.007%

    No Known Activations