© 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. 309
    Prev
    Next
    INDEX
    Explanations

    function definition or execution

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

    The neuron activates primarily on numeric tokens (digits or numbers).

    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
     lisäksi
    -1.00
     aktual
    -0.99
     koncentr
    -0.90
     menyesuaikan
    -0.90
     univerz
    -0.89
    isiä
    -0.89
    cibly
    -0.89
    РАЗ
    -0.88
    OTROS
    -0.88
    Ayrıca
    -0.88
    POSITIVE LOGITS
     then
    1.53
    その後
    1.09
     ristorante
    1.05
     luego
    0.95
    then
    0.93
     ulter
    0.93
     anschließend
    0.92
     subsequent
    0.89
     continued
    0.88
     both
    0.87
    Activations Density 0.004%

    No Known Activations