© 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. 10-GEMMASCOPE-RES-131K
    7. 75357
    Prev
    Next
    INDEX
    Explanations

    reply to communications

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

    The neuron fires strongly on instances of the word “reply” (in whatever casing or context).

    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
     arid
    -2.81
     pueden
    -2.66
     arcane
    -2.59
    N
    -2.58
     المسؤول
    -2.53
    老虎
    -2.47
     哪些
    -2.38
     aloof
    -2.36
     ‘‘
    -2.33
    蹂
    -2.33
    POSITIVE LOGITS
    鼕
    3.47
    it
    3.42
    e
    2.89
    }
    2.88
    
    2.75
     fédé
    2.73
    ruguay
    2.70
    緜
    2.63
    黩
    2.61
    羕
    2.58
    Activations Density 0.003%

    No Known Activations