© 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. 47890
    Prev
    Next
    INDEX
    Explanations

    purine bases and adenosine modifications

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

    chemical compounds, particularly nucleosides and nucleotides with specific chemical structures.

    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
    unsqueeze
    -0.78
     ester
    -0.72
     Moldova
    -0.70
     shingle
    -0.69
     Sarasota
    -0.69
     omnibus
    -0.69
     lī
    -0.69
    TextFormField
    -0.68
     услуг
    -0.68
     circums
    -0.68
    POSITIVE LOGITS
     nitrogen
    1.44
     pur
    1.43
     aden
    1.33
     bases
    1.24
     Pur
    1.22
    pur
    1.19
     Aden
    1.09
     Nitrogen
    1.06
     base
    1.05
    aden
    1.05
    Activations Density 0.161%

    No Known Activations