© 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. 2241
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

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

    The neuron fires strongly on numerical tokens (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
     Bangladesh
    -0.84
    Criterion
    -0.72
    Jonas
    -0.69
    יד
    -0.69
     unsettled
    -0.69
     Schenectady
    -0.69
     Macedonia
    -0.68
     Jonas
    -0.68
    strze
    -0.68
     >>
    -0.67
    POSITIVE LOGITS
     Cayman
    2.16
    Cay
    1.58
     CUC
    1.05
    centos
    1.04
     iguana
    0.96
     Montserrat
    0.94
    cay
    0.94
     Igu
    0.88
     McKee
    0.86
    🇰
    0.86
    Activations Density 0.010%

    No Known Activations