© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 70932
    Prev
    Next
    INDEX
    Explanations

    subscripted chemical formulas

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

    subscript numbers in chemical formulas and scientific notation.

    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_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
     has
    -1.80
     these
    -1.71
     appear
    -1.70
     their
    -1.65
     is
    -1.64
     should
    -1.61
     bringe
    -1.60
     &
    -1.59
     generalmente
    -1.59
     usually
    -1.55
    POSITIVE LOGITS
     samlet
    1.83
    栊
    1.70
     bygget
    1.68
     anillos
    1.66
     hectáreas
    1.65
     gramos
    1.60
     dekoratif
    1.59
     jaune
    1.58
     tratamientos
    1.55
    mining
    1.54
    Activations Density 0.034%

    No Known Activations