© 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. 129829
    Prev
    Next
    INDEX
    Explanations

    citations and bracketed references

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

    The neuron specializes in spotting numeric tokens (plain numbers and numeric values, including those with decimals).

    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
     foon
    -1.47
    xian
    -1.45
    laravel
    -1.27
    ✺
    -1.25
     Septembre
    -1.22
     professores
    -1.22
    VIATIONS
    -1.20
    wwww
    -1.18
     negru
    -1.17
    Université
    -1.16
    POSITIVE LOGITS
     what
    1.51
    我现在
    1.48
     would
    1.43
     cannot
    1.40
    以上です
    1.37
     become
    1.30
     someone
    1.30
     begin
    1.29
    是怎么回事
    1.26
    Following
    1.23
    Activations Density 0.147%

    No Known Activations