© 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. 34-GEMMASCOPE-RES-131K
    7. 98168
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron is detecting numeric tokens (i.e. standalone digits or numbers) 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_34/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
    +#+
    -0.83
    endet
    -0.77
    世界的
    -0.77
     Echin
    -0.75
    specs
    -0.74
     imp
    -0.71
    sterone
    -0.71
    Activator
    -0.71
     Zappa
    -0.69
    造
    -0.69
    POSITIVE LOGITS
     Catherine
    1.24
     David
    1.13
    Catherine
    1.10
     Elizabeth
    1.09
     Daniel
    1.08
     Michael
    1.07
     Katherine
    1.06
     Sarah
    1.06
     John
    1.05
     Matthew
    1.05
    Activations Density 0.011%

    No Known Activations