© 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. 70752
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

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

    This neuron activates on numeric literal tokens.

    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
    Zubereitung
    -1.82
     слегка
    -1.73
    erobic
    -1.73
     作り方
    -1.70
     if
    -1.65
    ☫
    -1.65
    ของ
    -1.62
    𖤍
    -1.61
    Jeśli
    -1.61
    zitter
    -1.59
    POSITIVE LOGITS
     “
    2.22
    ’
    2.17
    >
    1.90
    {
    1.83
    -
    1.80
     you
    1.65
    Y
    1.63
    )
    1.63
     território
    1.63
     
    1.61
    Activations Density 0.009%

    No Known Activations