© 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. 75643
    Prev
    Next
    INDEX
    Explanations

    extracts and scientific terms

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

    natural herbal or plant extracts in scientific or medical 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
    ULTS
    -0.71
     distributing
    -0.70
     dần
    -0.69
    optarg
    -0.68
    accéder
    -0.68
    Воспита
    -0.68
     resentment
    -0.67
     discharging
    -0.66
    入門
    -0.65
    ストック
    -0.65
    POSITIVE LOGITS
     extract
    1.63
     standardized
    1.58
     Extract
    1.45
     Standardized
    1.37
     standardization
    1.31
     standardised
    1.31
    Extract
    1.29
     extracts
    1.21
    extract
    1.20
     Standardi
    1.16
    Activations Density 0.072%

    No Known Activations