© 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. 314
    Prev
    Next
    INDEX
    Explanations

    stress

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

    the word "stress" in scientific contexts.

    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
    廨
    -2.86
     ſay
    -2.63
    ار
    -2.63
    ダブル
    -2.58
     ignited
    -2.56
     slated
    -2.56
     smacked
    -2.56
    硌
    -2.55
    猻
    -2.50
    ༈
    -2.45
    POSITIVE LOGITS
    鹛
    3.16
     is
    2.69
    that
    2.47
    𝘀
    2.42
    咐
    2.36
     l
    2.30
     partic
    2.27
    鋮
    2.25
    ↵
    2.19
     که
    2.17
    Activations Density 0.016%

    No Known Activations