© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65006
    Prev
    Next
    INDEX
    Explanations

    submicron manufacturing

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

    The neuron activates on numeric tokens (especially decimal‐formatted measurement values) in technical or scientific passages.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     BRASIL
    -1.13
     saisi
    -1.11
     funcion
    -1.08
     todav
    -1.08
     damos
    -1.05
     in
    -1.05
     informa
    -1.04
     specifik
    -1.02
     yayınları
    -1.02
     componentes
    -1.02
    POSITIVE LOGITS
     zugelassen
    1.25
    τας
    1.24
     mending
    1.21
     exh
    1.15
    edah
    1.12
     meistens
    1.11
     geschaffen
    1.10
     dieselbe
    1.09
     наличии
    1.09
     einzeln
    1.09
    Activations Density 0.002%

    No Known Activations