© 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. 7157
    Prev
    Next
    INDEX
    Explanations

    conditional gene expression

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

    scientific research methods and terminology in academic papers, particularly focusing on genetic and transgenic experimental approaches.

    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
     Murch
    -0.79
    EndTag
    -0.73
    rdf
    -0.71
    лича
    -0.71
     जान
    -0.71
    Predecesor
    -0.71
    PROPERTIES
    -0.71
     поса
    -0.71
    llano
    -0.71
     Therapie
    -0.70
    POSITIVE LOGITS
     Cre
    1.37
     conditional
    1.30
    Conditional
    1.24
     Conditional
    1.19
    conditional
    1.17
    Cre
    1.15
     flo
    0.98
     recombination
    0.96
     cre
    0.95
     conditionally
    0.94
    Activations Density 0.092%

    No Known Activations