© 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. 10-GEMMASCOPE-RES-131K
    7. 101833
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and numbers

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

    numerical measurements in scientific texts, particularly wavelengths and other physical parameters.

    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
     then
    -2.08
     you
    -2.06
     they
    -1.94
     to
    -1.91
     these
    -1.90
    ться
    -1.76
     this
    -1.66
     it
    -1.63
     them
    -1.61
     dieser
    -1.57
    POSITIVE LOGITS
    .
    1.93
    ഃ
    1.55
     Hinsicht
    1.52
    bró
    1.52
    tadır
    1.48
    Etimo
    1.38
    daad
    1.38
    Longueur
    1.34
    给人
    1.33
    绸
    1.31
    Activations Density 0.003%

    No Known Activations