© 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. 81429
    Prev
    Next
    INDEX
    Explanations

    cycle or cyclo compounds

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

    This neuron detects references to "cycle" and cycling-related terms, particularly in technical and chemical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    あげる
    -1.13
     altamente
    -1.09
     vastly
    -1.09
     creando
    -1.05
     cruelly
    -1.04
     crescente
    -1.01
     continually
    -1.00
    柔らかい
    -1.00
     髪型
    -1.00
     exceedingly
    -0.99
    POSITIVE LOGITS
     Cycle
    1.95
     cycle
    1.63
    cycle
    1.49
     CYCLE
    1.48
     Cycles
    1.44
    Cycle
    1.41
     cycles
    1.41
     cyclo
    1.34
     cyc
    1.32
     ciclo
    1.32
    Activations Density 0.038%

    No Known Activations