© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72897
    Prev
    Next
    INDEX
    Explanations

    LaTeX fractions

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

    This neuron fires on numeric tokens or digits, i.e. number literals in mathematical expressions.

    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
     WHAT
    -1.63
     There
    -1.59
     can
    -1.59
     就
    -1.53
                
    -1.51
     may
    -1.42
     In
    -1.32
     D
    -1.30
     might
    -1.30
                        
    -1.30
    POSITIVE LOGITS
     bricola
    2.03
     milieux
    1.81
    creates
    1.72
    粜
    1.72
     tives
    1.70
     oeuvres
    1.68
     conster
    1.68
     fantasma
    1.65
     kiu
    1.65
     auteurs
    1.64
    Activations Density 0.038%

    No Known Activations