© 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. 656
    Prev
    Next
    INDEX
    Explanations

    gene annotation and regulation

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

    scientific text related to genomics and gene sequences.

    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
     sequences
    -0.80
     Revenues
    -0.77
     Patents
    -0.74
    現地
    -0.73
     surnames
    -0.73
    werp
    -0.72
     sequence
    -0.71
     genomes
    -0.69
     patients
    -0.68
    犧
    -0.67
    POSITIVE LOGITS
     annotation
    0.78
    ventory
    0.76
     BRUN
    0.73
     contemporáneo
    0.73
    Annotation
    0.71
    ковым
    0.68
     коробки
    0.67
    canonical
    0.67
     lieb
    0.66
    university
    0.66
    Activations Density 0.029%

    No Known Activations