© 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. 104395
    Prev
    Next
    INDEX
    Explanations

    names ending in 'on', 'ion', or 'éon'

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

    names or identification of people or chemical compounds.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    0
    -3.09
     riservata
    -2.94
     tranquillo
    -2.83
    y
    -2.83
    there
    -2.75
     allarg
    -2.67
     sicura
    -2.64
     piú
    -2.61
    真的是
    -2.61
     Of
    -2.61
    POSITIVE LOGITS
    ৢ
    2.50
    n
    2.42
     replete
    2.33
    骉
    2.22
    儇
    2.20
    ↵↵
    2.20
    
    2.13
    嫆
    2.11
     längst
    2.03
     vanguardia
    2.03
    Activations Density 0.187%

    No Known Activations