© 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. 33230
    Prev
    Next
    INDEX
    Explanations

    Te Rau Hinengaro

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

    This neuron detects numeric tokens—that is, sequences of digits (including numeric escape‐sequence values).

    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
    がある
    -1.13
    內容簡介
    -0.96
    唄
    -0.96
    があり
    -0.95
    を
    -0.94
     ITEMS
    -0.94
    もあります
    -0.93
    čnosti
    -0.92
    があります
    -0.91
     maig
    -0.91
    POSITIVE LOGITS
     However
    1.17
     But
    1.05
    ことが
    0.99
     similarly
    0.98
     This
    0.97
    んですが
    0.97
     beteiligt
    0.94
    ことも
    0.94
     proget
    0.93
    ところは
    0.92
    Activations Density 0.005%

    No Known Activations