© 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. 10527
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

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

    This neuron fires on numeric literals that include a decimal point (i.e. fractional 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
     komfor
    -1.80
    garmin
    -1.66
     ILLUSTRATIONS
    -1.59
     their
    -1.58
     Livro
    -1.55
    狃
    -1.52
     fournisseur
    -1.51
     APPELL
    -1.47
    camara
    -1.47
     resultat
    -1.46
    POSITIVE LOGITS
    1
    1.77
    4
    1.74
    5
    1.73
    9
    1.70
    urized
    1.64
    2
    1.55
     it
    1.50
    AL
    1.48
    rd
    1.48
    7
    1.45
    Activations Density 0.016%

    No Known Activations