© 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. 10-GEMMASCOPE-RES-131K
    7. 19310
    Prev
    Next
    INDEX
    Explanations

    isotope labeling

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

    isotope labels and radioactive elements in scientific research contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects numeric isotope labels (mass numbers) attached to chemical element symbols.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     artistico
    -1.93
     Futbol
    -1.93
     masina
    -1.88
     picha
    -1.84
     stiker
    -1.82
     ingenting
    -1.81
    蚍
    -1.81
     nini
    -1.81
     dolar
    -1.78
     pompa
    -1.77
    POSITIVE LOGITS
    ↵↵
    1.80
    ↵
    1.68
    .,
    1.63
    amentlich
    1.51
    ıyorum
    1.50
    厹
    1.48
    wantErr
    1.47
     of
    1.45
     elaborate
    1.43
     Publikum
    1.43
    Activations Density 0.039%

    No Known Activations