© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10429
    Prev
    Next
    INDEX
    Explanations

    legal and technical document separators

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

    The neuron primarily activates on numeric tokens, especially standalone integers and decimal 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_10/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
     on
    -1.62
     with
    -1.62
     only
    -1.61
     zufolge
    -1.55
    </u>
    -1.51
     überprü
    -1.51
     gewähr
    -1.48
     тільки
    -1.46
     verfol
    -1.44
     adds
    -1.39
    POSITIVE LOGITS
     himmel
    1.74
     elek
    1.61
    tä
    1.55
    
    1.53
    hdysval
    1.53
     {
    1.52
     reguli
    1.52
     damen
    1.52
    lgari
    1.52
     kjer
    1.50
    Activations Density 0.005%

    No Known Activations