© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102835
    Prev
    Next
    INDEX
    Explanations

    approximate numerical values

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

    The neuron activates on numeric tokens—especially measurements or quantities, including both integers and decimals.

    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
    then
    -1.70
     then
    -1.64
    樉
    -1.48
    鼍
    -1.48
     Then
    -1.48
     estadounid
    -1.47
    
    -1.45
     europé
    -1.44
     Luego
    -1.42
     ſind
    -1.40
    POSITIVE LOGITS
     had
    1.63
    ньому
    1.55
    籥
    1.49
     increase
    1.47
     hundreds
    1.45
     as
    1.44
    upyter
    1.42
     minerales
    1.41
    犊
    1.40
     caused
    1.39
    Activations Density 0.036%

    No Known Activations