© 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. 119382
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms

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

    code or documentation annotations and references in technical content.

    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
     primer
    -0.76
     Ι
    -0.75
     ras
    -0.67
    高原
    -0.66
     рука
    -0.64
     Marcos
    -0.63
    eig
    -0.63
     premises
    -0.63
     AV
    -0.63
     EL
    -0.61
    POSITIVE LOGITS
     ngành
    0.76
    łyż
    0.75
    Peng
    0.74
    ńczy
    0.72
     negó
    0.71
     bahç
    0.69
     émer
    0.69
     Küche
    0.69
    maar
    0.69
    Жан
    0.68
    Activations Density 0.093%

    No Known Activations