© 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. 90805
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron strongly activates on numeric tokens (literal 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
     thus
    -1.00
    thus
    -0.94
     hence
    -0.94
    therefore
    -0.94
    ᧐
    -0.93
     wyróż
    -0.92
    itores
    -0.90
     ainsi
    -0.90
    hence
    -0.88
     примеру
    -0.88
    POSITIVE LOGITS
     descri
    0.87
     Bennet
    0.85
    はこの
    0.85
     manhã
    0.85
     każdej
    0.84
     этих
    0.82
     gover
    0.82
    Каждый
    0.82
    اریخ
    0.78
     каждый
    0.77
    Activations Density 0.179%

    No Known Activations