© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44293
    Prev
    Next
    INDEX
    Explanations

    scientific analytical methods

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

    scientific methodologies described in research papers, particularly analytical methods for detection or measurement.

    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
    ȴ
    -1.38
     protože
    -1.34
     about
    -1.34
     preferencias
    -1.25
    γωγ
    -1.24
     udrž
    -1.23
    jący
    -1.22
    през
    -1.22
     první
    -1.21
     概要
    -1.21
    POSITIVE LOGITS
     procedure
    1.83
    </u>
    1.56
     method
    1.55
     venerdì
    1.50
     to
    1.50
    digitalWrite
    1.45
     technique
    1.45
     techniques
    1.39
     зрения
    1.39
    kań
    1.38
    Activations Density 0.454%

    No Known Activations