© 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. 34-GEMMASCOPE-RES-131K
    4. 58862
    Prev
    Next
    INDEX
    Explanations

    essential biological molecules or ingredients

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

    scientific descriptions of chemical compounds, particularly in academic or product 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_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
     newbies
    -0.96
     pernic
    -0.96
     newcomers
    -0.94
     nové
    -0.93
    mpz
    -0.88
     observables
    -0.86
     melatonin
    -0.85
    뻗
    -0.85
     habitable
    -0.84
    enic
    -0.84
    POSITIVE LOGITS
     molecule
    1.28
     found
    1.28
     widely
    1.20
     component
    1.15
     also
    1.05
     naturally
    1.05
     hormone
    1.00
     ingredient
    0.99
     key
    0.97
     essential
    0.96
    Activations Density 0.316%

    No Known Activations