© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118767
    Prev
    Next
    INDEX
    Explanations

    aldehyde and dehydrogenase

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

    chemical compounds ending in "dehyde" or "aldehyde", particularly in scientific contexts.

    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_10/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
    \},
    -2.17
    甞
    -2.13
    ”،
    -2.06
    ⧠
    -1.99
    甚至是
    -1.98
     élevé
    -1.98
    ()){
    
    -1.97
     всего
    -1.95
    	
    -1.95
    蕷
    -1.93
    POSITIVE LOGITS
    “
    2.72
    ции
    2.50
    
    2.30
    棪
    2.19
     maanden
    2.16
    豨
    2.11
     activiteiten
    2.03
     لأنه
    2.00
    1
    1.93
     Química
    1.92
    Activations Density 0.023%

    No Known Activations