© 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. 86006
    Prev
    Next
    INDEX
    Explanations

    plant breeding

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

    terms related to plant breeding and genetics.

    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
    astify
    -1.41
    缡
    -1.39
    lierung
    -1.39
    furter
    -1.30
     Femmes
    -1.26
     pandémie
    -1.25
    digheden
    -1.25
    pektrum
    -1.23
    izace
    -1.22
    вушка
    -1.20
    POSITIVE LOGITS
    </b>
    1.31
    Opin
    1.20
    Kult
    1.16
    </sup>
    1.13
     viena
    1.13
     Papst
    1.11
     doloroso
    1.04
     Mostrar
    1.02
    Karakter
    1.02
     moks
    1.02
    Activations Density 0.102%

    No Known Activations