© 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. 22-GEMMASCOPE-RES-131K
    4. 13564
    Prev
    Next
    INDEX
    Explanations

    code comments and questions

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

    The neuron is keyed to occurrences of the identifier “Text” (as in the System.Text using‐directive) in C# code.

    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
    んですよね
    -1.18
     ayudó
    -1.16
    おかしい
    -1.13
     envía
    -1.08
     ícone
    -1.05
     apoya
    -1.05
    ''');
    -1.05
     levanta
    -1.05
     armées
    -1.04
    AxisSize
    -1.03
    POSITIVE LOGITS
     and
    1.77
    。
    
    1.16
    </b>
    1.10
    .
    
    1.07
    尤其是
    1.05
    ,
    1.02
    zten
    1.00
    luents
    0.99
    ztes
    0.98
    tigste
    0.98
    Activations Density 0.001%

    No Known Activations