© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129776
    Prev
    Next
    INDEX
    Explanations

    medical , Slavic , technical terms

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

    words in non-English languages, particularly Slavic and Baltic languages.

    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
     actual
    -1.47
     innamor
    -1.42
    stdc
    -1.42
     quelli
    -1.34
    actual
    -1.34
     otras
    -1.32
    Leírás
    -1.32
    颡
    -1.29
    Actual
    -1.27
    要不要
    -1.26
    POSITIVE LOGITS
     MATHEMATICAL
    1.71
     (_.
    1.52
     ECONOMICS
    1.48
     this
    1.37
     Tricks
    1.36
     POLLUTION
    1.36
     Epidemiology
    1.35
     BorderLayout
    1.34
    ſſen
    1.33
     TECHNIQUES
    1.32
    Activations Density 0.032%

    No Known Activations