© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19772
    Prev
    Next
    INDEX
    Explanations

    reply to

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

    The neuron strongly activates on instances of the “reply to” construction (and related reply/replies tokens).

    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
    </h4>
    -2.28
     pueden
    -2.09
     nueva
    -2.06
     і
    -2.00
     unite
    -1.95
    </sup>
    -1.92
    ON
    -1.89
    蹂
    -1.85
     время
    -1.80
     e
    -1.80
    POSITIVE LOGITS
    }
    2.64
    鼕
    2.53
    
    2.31
     fédé
    2.06
     mattino
    2.00
     offerts
    1.99
     clc
    1.99
    緜
    1.97
     tramonto
    1.90
     administratif
    1.89
    Activations Density 0.005%

    No Known Activations