© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113714
    Prev
    Next
    INDEX
    Explanations

    chemical notation and abbreviations like f.lux

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

    abbreviations followed by periods, particularly in scientific and mathematical contexts.

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

    The neuron fires on occurrences of the Greek letter “μ” (mu) used in inorganic‐chemistry formulas to denote bridging ligands or atoms.

    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
     לאחר
    -1.41
    Ş
    -1.41
    </h3>
    -1.41
    warzys
    -1.34
     británica
    -1.30
     många
    -1.28
     disminuir
    -1.28
     then
    -1.28
    เกง
    -1.28
    ↵↵
    -1.23
    POSITIVE LOGITS
     that
    1.88
     for
    1.75
     any
    1.52
    ....
    1.48
    .....
    1.45
    
    1.43
     garçon
    1.40
     nasceu
    1.40
    .(
    1.38
     with
    1.37
    Activations Density 0.062%

    No Known Activations