© 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. 34-GEMMASCOPE-RES-131K
    7. 86828
    Prev
    Next
    INDEX
    Explanations

    conversion and transition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     preparando
    -0.91
    同士
    -0.87
     entrando
    -0.85
    のだろう
    -0.85
     from
    -0.84
    ようになります
    -0.84
    の可能性
    -0.84
    に追加
    -0.79
    FromString
    -0.79
    кновен
    -0.78
    POSITIVE LOGITS
     conversion
    1.81
     ratio
    1.63
     converter
    1.60
     transition
    1.56
    conversion
    1.34
    converter
    1.21
     Conversion
    1.20
     transformation
    1.19
    Converter
    1.19
     Converter
    1.18
    Activations Density 0.051%

    No Known Activations