© 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. 22-GEMMASCOPE-RES-131K
    4. 98172
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

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

    This neuron fires on numeric tokens (digits or numeric literals) in code or text.

    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
     otra
    -1.04
     (
    -1.01
     (*(
    -0.95
    ignac
    -0.94
    ーマー
    -0.91
     fist
    -0.89
    田村
    -0.89
     Cowboys
    -0.88
     Сергей
    -0.88
    enosti
    -0.88
    POSITIVE LOGITS
     betreft
    1.09
     coupled
    0.94
     plezier
    0.93
    estina
    0.92
     placent
    0.91
     ambientale
    0.91
    
    0.91
     uitzicht
    0.90
    啫
    0.90
     Junto
    0.88
    Activations Density 0.030%

    No Known Activations