© 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. 23453
    Prev
    Next
    INDEX
    Explanations

    nasa and space centers

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

    The neuron selectively activates on numeric tokens—especially years, dates, and other digits—often found in structured infobox–style data.

    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
     hương
    -0.79
    nabis
    -0.74
     kosong
    -0.72
     belajar
    -0.72
    EDI
    -0.72
    entlicher
    -0.72
     Malone
    -0.71
    Sizer
    -0.71
     CLIP
    -0.71
     
    -0.71
    POSITIVE LOGITS
     Kennedy
    1.50
    Kennedy
    1.37
     Goddard
    1.33
     NASA
    1.27
    NASA
    1.09
     JSC
    1.07
     Johnson
    1.06
     Cape
    1.06
     Space
    1.03
     KENN
    1.02
    Activations Density 0.050%

    No Known Activations