© 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. 1240
    Prev
    Next
    INDEX
    Explanations

    chemical bonds, vibrations, and resonances

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

    chemical bonds and molecular structures in scientific literature, especially those involving spectroscopy and vibrational analysis.

    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
    他们
    -1.69
    螓
    -1.64
     dezelve
    -1.59
     stoff
    -1.58
     regionale
    -1.56
     bedro
    -1.56
     ofte
    -1.55
     assic
    -1.55
     fournis
    -1.54
    ⩴
    -1.54
    POSITIVE LOGITS
     in
    2.28
     at
    2.03
     during
    1.80
     nestled
    1.73
     within
    1.73
     that
    1.66
     throughout
    1.63
     over
    1.62
     of
    1.55
     this
    1.54
    Activations Density 0.085%

    No Known Activations