© 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. 82930
    Prev
    Next
    INDEX
    Explanations

    nanopillars, polymers, emission, DNA, CO2

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

    chemical and scientific terms in academic research papers.

    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_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
     subcutaneous
    -0.73
    仗
    -0.71
    тник
    -0.70
    を失
    -0.70
     blindness
    -0.69
    yim
    -0.67
     млрд
    -0.66
    Arquivo
    -0.66
     marge
    -0.66
     proud
    -0.65
    POSITIVE LOGITS
    为什么要
    0.90
    介護
    0.81
    Mű
    0.75
    ⾯
    0.75
     Interval
    0.71
    ("$.
    0.70
    Nh
    0.69
    verick
    0.69
    конча
    0.68
    Ja
    0.67
    Activations Density 0.051%

    No Known Activations