© 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. 124156
    Prev
    Next
    INDEX
    Explanations

    Gaucher, gauged, gauze, gauge

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

    The neuron responds to occurrences of the letter sequence “gau” (e.g. in Gaucher, gauged, gauze, gauge, etc.).

    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
     That
    -3.48
    that
    -2.88
     was
    -2.56
    as
    -2.42
    逦
    -2.33
     schützen
    -2.31
     که
    -2.30
     shuffled
    -2.23
    ></
    -2.20
    罢了
    -2.19
    POSITIVE LOGITS
    ⮜
    2.64
     ſy
    2.52
    廰
    2.52
    糨
    2.52
    ⚋
    2.48
    anthene
    2.38
     graced
    2.38
    鼱
    2.36
     και
    2.30
     prendere
    2.25
    Activations Density 0.003%

    No Known Activations