© 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. 60228
    Prev
    Next
    INDEX
    Explanations

    process stages or sequences

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

    The neuron activates on occurrences of the word “process” (and its variants like “processing”) in the text.

    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
    隳
    -3.95
    蟊
    -2.78
     améli
    -2.77
    鐿
    -2.70
     ity
    -2.70
     
    -2.64
    ’
    -2.59
    삵
    -2.59
    鲞
    -2.58
    皤
    -2.56
    POSITIVE LOGITS
     }
    3.27
    It
    2.83
    霂
    2.81
     cbd
    2.78
     l
    2.75
    鋮
    2.75
     =
    2.63
     reputable
    2.58
    ☫
    2.58
    })
    2.55
    Activations Density 0.051%

    No Known Activations