© 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. 97742
    Prev
    Next
    INDEX
    Explanations

    built constructed erected

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

    The neuron fires on numeric tokens, especially years and other multi‐digit 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_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
     zowel
    -1.03
    Zunanje
    -1.00
     verschillende
    -1.00
    ⎼
    -1.00
    ेड
    -0.96
     написа
    -0.95
     greu
    -0.94
    creates
    -0.94
    Concerning
    -0.94
    ๊ก
    -0.92
    POSITIVE LOGITS
     on
    2.28
     adjacent
    1.51
     using
    1.45
     financed
    1.38
     next
    1.34
     near
    1.31
     beside
    1.27
     funded
    1.25
     to
    1.23
     funds
    1.16
    Activations Density 0.074%

    No Known Activations