© 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. 34053
    Prev
    Next
    INDEX
    Explanations

    isotopes and chemical elements

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

    The neuron identifies isotope numbers in scientific contexts, particularly atomic and nuclear elements like Cesium-137, Strontium-90, or Carbon-13.

    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_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
     if
    -1.29
     areas
    -1.25
     area
    -1.14
    徒歩
    -1.12
    返品
    -1.00
     Arten
    -0.98
     distinta
    -0.98
    maxY
    -0.97
    OrDefault
    -0.95
     resur
    -0.95
    POSITIVE LOGITS
    Karena
    1.23
    Föld
    1.18
    Pada
    1.16
    енная
    1.13
     naturligt
    1.09
     protokol
    1.09
    chent
    1.09
     kursi
    1.08
    diğimiz
    1.07
     ganska
    1.02
    Activations Density 0.016%

    No Known Activations