© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69190
    Prev
    Next
    INDEX
    Explanations

    scale with measurement or transaction contexts

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

    The neuron reliably fires on occurrences of the word “scale.”

    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
    
    -3.88
    妧
    -2.91
     Instead
    -2.89
     However
    -2.75
     Incidentally
    -2.66
    鷙
    -2.64
     Except
    -2.63
     Therefore
    -2.63
    렷
    -2.63
     Now
    -2.56
    POSITIVE LOGITS
    K
    3.31
    e
    3.16
    C
    3.02
    You
    2.95
    Ⲉ
    2.94
    of
    2.89
    蛧
    2.86
    ଝ
    2.81
    鋦
    2.78
    ﮦ
    2.72
    Activations Density 0.017%

    No Known Activations