© 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. 10-GEMMASCOPE-RES-131K
    7. 60579
    Prev
    Next
    INDEX
    Explanations

    dried [food and plant matter]

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

    descriptions of dried organic materials like plants, foods, or biological samples.

    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
    (
    -2.84
    ܜ
    -2.72
    ka
    -2.66
     to
    -2.66
    \
    -2.63
    秝
    -2.50
    p
    -2.48
    j
    -2.44
    摧
    -2.38
    -2.36
    POSITIVE LOGITS
     começaram
    3.06
     passaram
    2.81
     tinham
    2.66
     ficaram
    2.64
     fizeram
    2.64
     estavam
    2.58
     tiveram
    2.58
    廡
    2.53
    是真的
    2.50
     aktuelle
    2.48
    Activations Density 0.004%
    No Known Activations