© 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. 10-GEMMASCOPE-RES-131K
    7. 71172
    Prev
    Next
    INDEX
    Explanations

    late onset

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

    The neuron activates on numeric tokens (including hyphenated and decimal numbers).

    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
      
    -2.23
    medriver
    -1.99
    settled
    -1.93
    fanfic
    -1.91
     станет
    -1.88
     ก็
    -1.88
    </h4>
    -1.80
    🫅
    -1.80
    زيون
    -1.78
     gesammelt
    -1.77
    POSITIVE LOGITS
    b
    2.36
     They
    2.31
    焢
    2.05
     bahwa
    1.96
    y
    1.95
    Даже
    1.89
    end
    1.88
    h
    1.86
    ts
    1.85
    ana
    1.84
    Activations Density 0.008%

    No Known Activations