© 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. 75160
    Prev
    Next
    INDEX
    Explanations

    tetra, tri, di prefixes in chemical names

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

    chemical prefixes like "tetra", "di", "tri", and "poly" in scientific chemical names.

    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
     to
    -3.30
    .
    -2.66
     in
    -2.42
     
    -2.33
     The
    -2.20
     of
    -2.13
     for
    -2.09
     into
    -2.03
     “
    -1.88
     kind
    -1.80
    POSITIVE LOGITS
     costuras
    2.75
     parfü
    2.52
     parfüm
    2.36
     beslu
    2.25
     estampado
    2.22
     dekoratif
    2.22
     bolsos
    2.19
     fédé
    2.14
     هستند
    2.14
     resistentes
    2.13
    Activations Density 0.164%

    No Known Activations