© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57741
    Prev
    Next
    INDEX
    Explanations

    cyclic antidepressants

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

    chemical and pharmaceutical compound names, particularly those ending with suffixes like "ine," "ide," "ate," and other medication-related terminology.

    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
     berkembang
    -0.78
     information
    -0.76
    ῥ
    -0.76
    óra
    -0.75
    tando
    -0.73
     schwä
    -0.72
    études
    -0.72
     Nickelodeon
    -0.71
     emailed
    -0.71
     Invisalign
    -0.71
    POSITIVE LOGITS
    Salvar
    0.98
     preparations
    0.78
     Coff
    0.78
    GPI
    0.78
    Crow
    0.77
    Powered
    0.76
    .\"
    0.76
    Լ
    0.75
     Preparations
    0.75
     vårt
    0.74
    Activations Density 0.264%

    No Known Activations