© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99589
    Prev
    Next
    INDEX
    Explanations

    supplement/suppl

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

    scientific journal citations and reference numbers.

    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
     Universidade
    -0.77
    inthians
    -0.74
     Ně
    -0.73
     corps
    -0.70
     Pacífico
    -0.70
    lowercase
    -0.69
    udge
    -0.69
    setLong
    -0.67
     Nguyễn
    -0.66
     بده
    -0.66
    POSITIVE LOGITS
     supplement
    3.33
     Supplement
    2.72
     supplements
    2.64
    supplement
    2.36
    Supplement
    2.17
     Supplements
    2.13
     Suppl
    2.08
     supplementary
    2.08
     supplemental
    2.05
     SUPPLEMENT
    2.02
    Activations Density 0.030%

    No Known Activations