© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128178
    Prev
    Next
    INDEX
    Explanations

    plants and growth

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

    words related to gardening, farming, and plants, particularly focusing on items like "chicken coops," crops, and plant varieties.

    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
     unga
    -1.47
     haup
    -1.38
     afs
    -1.27
     salomon
    -1.27
     bloem
    -1.26
     koel
    -1.23
     jule
    -1.23
     fatis
    -1.22
     hvil
    -1.21
     saveiro
    -1.19
    POSITIVE LOGITS
     them
    1.54
     my
    1.45
     be
    1.28
     మరి
    1.27
    řízení
    1.25
     tell
    1.22
     about
    1.16
     myself
    1.15
    ありますか
    1.13
     You
    1.13
    Activations Density 0.063%

    No Known Activations