© 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. 61192
    Prev
    Next
    INDEX
    Explanations

    it was

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

    This neuron detects numeric expressions, especially numbers with decimals or other numerical measurements.

    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
    Its
    -1.50
    旁邊
    -1.38
     அத
    -1.25
    却是
    -1.23
    as
    -1.23
    これらの
    -1.23
     of
    -1.21
     It
    -1.20
    也只能
    -1.19
     attacco
    -1.19
    POSITIVE LOGITS
     his
    1.63
     魔法
    1.45
    }
    
    1.23
     febbraio
    1.23
    }=
    1.21
     tepi
    1.17
    {
    
    1.17
     into
    1.16
    محمد
    1.16
     septembre
    1.14
    Activations Density 0.165%

    No Known Activations