© 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. 22-GEMMASCOPE-RES-131K
    7. 130356
    Prev
    Next
    INDEX
    Explanations

    The neuron specifically detects occurrences of the word “original.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    origin or first version

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     presently
    -1.09
    ন
    -0.99
    currently
    -0.97
    żs
    -0.97
     künftig
    -0.95
    擄
    -0.91
    SetFont
    -0.90
     currently
    -0.90
    新たに
    -0.90
     other
    -0.89
    POSITIVE LOGITS
     original
    1.69
     originally
    1.60
     originales
    1.36
     Originally
    1.35
     originale
    1.31
    original
    1.28
     intended
    1.27
     Original
    1.26
    原
    1.25
    Original
    1.24
    Activations Density 0.059%

    No Known Activations