© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102063
    Prev
    Next
    INDEX
    Explanations

    Effect, When, Tumour, Alkaline

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

    newline characters with whitespace, particularly in code and technical documents.

    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
    鹇
    -1.62
     disponibilités
    -1.48
     DÉ
    -1.48
     savons
    -1.47
     chirurgie
    -1.41
    fers
    -1.40
     تصميم
    -1.39
     schreef
    -1.38
     patienter
    -1.38
     pérd
    -1.36
    POSITIVE LOGITS
     two
    1.47
     started
    1.41
     ostensibly
    1.36
     less
    1.35
    Those
    1.35
     będziemy
    1.30
     innumerable
    1.27
     nhưng
    1.26
     腳
    1.26
    ürnberg
    1.25
    Activations Density 0.000%

    No Known Activations