© 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. 65971
    Prev
    Next
    INDEX
    Explanations

    code comments and metadata

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

    The neuron activates on numeric tokens—that is, any standalone sequences of digits (e.g. version numbers, years, counts).

    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
     before
    -1.05
     gotas
    -1.01
    spender
    -0.96
    لول
    -0.96
     oddly
    -0.95
     some
    -0.94
     by
    -0.94
     all
    -0.91
     contar
    -0.91
     Agosto
    -0.91
    POSITIVE LOGITS
    -&
    1.09
    Ô
    1.00
     stalwart
    1.00
     delightfully
    0.98
     exuber
    0.98
    繋が
    0.97
     verschillende
    0.96
     ******
    0.94
     continually
    0.94
     Dinas
    0.93
    Activations Density 0.001%

    No Known Activations