© 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. 22-GEMMASCOPE-RES-131K
    7. 28331
    Prev
    Next
    INDEX
    Explanations

    original or raw data

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

    The neuron fires on tokens naming “raw,” “original,” “source,” “origin,” “url,” “data,” or similar fields—that is, variable or parameter names referring to original/raw/source data or URLs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     mulher
    -1.03
     특
    -0.99
     alcune
    -0.98
     inizia
    -0.97
     miatt
    -0.91
    inici
    -0.91
     paltry
    -0.90
     aproape
    -0.89
     trám
    -0.88
     distin
    -0.86
    POSITIVE LOGITS
    original
    1.48
     raw
    1.45
     original
    1.29
     unmodified
    1.19
     originals
    1.16
    Original
    1.13
    原始
    1.09
     originales
    1.09
     originale
    1.06
    rebbe
    1.03
    Activations Density 0.052%

    No Known Activations