© 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. 54126
    Prev
    Next
    INDEX
    Explanations

    legal names and case identifiers

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

    The neuron strongly activates on numeric tokens (strings of digits, often with decimals), i.e. it detects 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
     penyanyi
    -1.00
    ～～
    -0.92
    டுக
    -0.91
     kekasih
    -0.91
    鈎
    -0.90
    谆
    -0.88
    ﺅ
    -0.88
    AKI
    -0.88
    恚
    -0.87
    義務
    -0.86
    POSITIVE LOGITS
     eröffnet
    0.95
    corrhi
    0.94
    oliber
    0.90
     (!__
    0.88
    GetAsync
    0.87
     gefertigt
    0.85
    cancellation
    0.84
     up
    0.84
     cualquiera
    0.83
     incontra
    0.83
    Activations Density 0.002%

    No Known Activations