© 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. 104000
    Prev
    Next
    INDEX
    Explanations

    questions and code identifiers

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

    opening parentheses or quotes that begin parameter lists or string values in code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     fenêtres
    -1.98
     dépenses
    -1.89
    และ
    -1.86
    鸨
    -1.74
    approximately
    -1.73
    两只
    -1.73
     qualités
    -1.72
     acheteurs
    -1.72
    commonly
    -1.70
    
    -1.70
    POSITIVE LOGITS
     juga
    1.74
     through
    1.64
     one
    1.61
     at
    1.55
     without
    1.55
     と
    1.54
     Also
    1.52
     поговори
    1.51
    </h2>
    1.49
     も
    1.48
    Activations Density 0.001%

    No Known Activations