© 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. 75482
    Prev
    Next
    INDEX
    Explanations

    embryo development

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

    This neuron detects references to embryos or embryonic development 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
    
    -2.31
     passés
    -2.31
    //};
    -2.27
    就直接
    -2.20
     smacked
    -2.19
    S
    -2.19
    縒
    -2.19
     unſ
    -2.16
    」　
    -2.14
     assures
    -2.13
    POSITIVE LOGITS
    婠
    2.20
    I
    2.11
     September
    2.03
     leichten
    2.03
     This
    2.02
    h
    2.02
     February
    2.00
     November
    1.98
    i
    1.98
     zwanzig
    1.95
    Activations Density 0.009%

    No Known Activations