© 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. 73712
    Prev
    Next
    INDEX
    Explanations

    keto and related compounds

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

    medical and chemical terms related to ketones and acidosis.

    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
     spotify
    -0.79
     Perm
    -0.74
    ventional
    -0.73
     Pottery
    -0.71
     Sulf
    -0.71
    း
    -0.69
     Malte
    -0.68
     Balk
    -0.68
     gladi
    -0.68
     amg
    -0.67
    POSITIVE LOGITS
     keto
    1.73
     ke
    1.64
     Keto
    1.51
     ketone
    1.44
     Ke
    1.34
     Ket
    1.30
    keto
    1.30
     ketones
    1.23
     ке
    1.20
     metabolic
    1.15
    Activations Density 0.034%

    No Known Activations