© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13824
    Prev
    Next
    INDEX
    Explanations

    shipping contents

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

    The neuron activates on numeric expressions (integers or decimals) in the 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
     răsp
    -1.02
     seks
    -1.02
     BEN
    -1.00
    ambo
    -0.97
     benutzt
    -0.97
    部分を
    -0.95
     inconsciente
    -0.95
     fout
    -0.95
     desarrolló
    -0.95
    だけです
    -0.93
    POSITIVE LOGITS
     sparkly
    1.14
     Perhaps
    1.01
     (
    1.01
     Sadly
    1.00
     Quite
    0.94
     weirdly
    0.94
     in
    0.94
    ;
    0.89
     Several
    0.89
     Very
    0.88
    Activations Density 0.139%

    No Known Activations