© 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. 39960
    Prev
    Next
    INDEX
    Explanations

    code syntax and punctuation

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

    The neuron is triggered by numeric tokens (digits or numbers) in the text.

    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
     тщательно
    -0.98
    プロフィール
    -0.91
    Maak
    -0.89
    ♩
    -0.88
    ógrafo
    -0.87
    Kommentare
    -0.85
    Inne
    -0.84
    ὗ
    -0.84
     套装
    -0.84
    ndose
    -0.83
    POSITIVE LOGITS
    suffix
    0.94
    kai
    0.93
     who
    0.89
     with
    0.86
     followed
    0.85
     it
    0.85
     seguida
    0.82
    帷
    0.81
     continue
    0.81
    続けて
    0.81
    Activations Density 0.031%

    No Known Activations