© 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. 12324
    Prev
    Next
    INDEX
    Explanations

    boiled egg

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

    words related to boiling or heating water, particularly in cooking instructions.

    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_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
    饧
    -1.75
    垍
    -1.65
     "..\..\..\
    -1.58
     didn
    -1.57
    ﹶ
    -1.53
    舠
    -1.49
     wich
    -1.48
     unſ
    -1.45
    此时的
    -1.45
     ,,
    -1.44
    POSITIVE LOGITS
    ल
    1.82
    ции
    1.74
     interessantes
    1.52
    .
    1.46
                
    1.45
    taminophen
    1.45
    
    1.44
    The
    1.43
    
    1.43
    Component
    1.41
    Activations Density 0.021%

    No Known Activations