© 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. 28605
    Prev
    Next
    INDEX
    Explanations

    Download, item, Revealed, Structural, Copyright

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

    The neuron strongly activates on tokens made up of digits (numeric strings or identifiers, e.g. long sequences of numbers in URLs or codes).

    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
     it
    -1.12
    িয়া
    -1.08
     febru
    -0.98
     but
    -0.98
    anguardia
    -0.94
     who
    -0.93
     prenez
    -0.93
    dekat
    -0.92
    ificação
    -0.90
     balón
    -0.90
    POSITIVE LOGITS
     ayudará
    0.99
    acheter
    0.98
     ricevere
    0.97
    owany
    0.94
     chronicles
    0.93
    ۔
    0.90
    通過
    0.89
    ῃ
    0.89
     vulnerable
    0.89
    かというと
    0.89
    Activations Density 0.004%

    No Known Activations