© 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. 10-GEMMASCOPE-RES-131K
    7. 40652
    Prev
    Next
    INDEX
    Explanations

    saturation and analysis

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

    The neuron detects occurrences of “saturation” (and its variants like “saturated”).

    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
     diza
    -3.25
    鬭
    -2.94
    
    -2.78
    댔
    -2.73
     Ahnung
    -2.72
     they
    -2.69
    馓
    -2.69
    皷
    -2.67
    %")
    -2.63
    ⇴
    -2.63
    POSITIVE LOGITS
    ↵
    4.06
     intensely
    2.81
    s
    2.77
     inherently
    2.63
     abundant
    2.41
     programs
    2.41
     perpetually
    2.41
     unrelenting
    2.41
     enormous
    2.39
     artificially
    2.36
    Activations Density 0.003%

    No Known Activations