© 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. 34-GEMMASCOPE-RES-131K
    7. 50376
    Prev
    Next
    INDEX
    Explanations

    Pilgrim or pilgrimage

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

    The neuron is a simple “reading‐order” detector that gradually increases its activation the further you progress into the document.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    🔕
    -0.72
    Partners
    -0.72
    kranz
    -0.71
     Partners
    -0.69
    疎
    -0.68
    entri
    -0.66
    partners
    -0.66
    cene
    -0.65
     ActionResult
    -0.65
     Zn
    -0.65
    POSITIVE LOGITS
     pilgrim
    2.48
     pilgrims
    2.48
     Pilgrim
    2.06
     pilgrimage
    2.02
     Pilgrims
    1.96
    Pil
    1.55
     peregr
    1.52
     travelers
    1.48
     pilgri
    1.48
    pil
    1.47
    Activations Density 0.026%

    No Known Activations