© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130322
    Prev
    Next
    INDEX
    Explanations

    chemical formula components

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

    chemical structures and formulas in scientific papers.

    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
    -1.34
     several
    -1.29
     even
    -1.29
     on
    -1.27
     many
    -1.26
     while
    -1.21
     or
    -1.16
     time
    -1.13
     high
    -1.13
     want
    -1.12
    POSITIVE LOGITS
     boister
    1.45
     cinq
    1.44
    another
    1.38
     EIGHT
    1.34
     FOUR
    1.34
    completely
    1.30
     SEVEN
    1.29
     SIX
    1.27
     cuatro
    1.26
     Transfermarkt
    1.25
    Activations Density 0.110%

    No Known Activations