© 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. 962
    Prev
    Next
    INDEX
    Explanations

    applying soil amendments and fertilizers

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

    research related to soil amendments, fertilizers, and agricultural treatments.

    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
    ECONDS
    -0.83
    膳
    -0.78
     nullable
    -0.76
    orderby
    -0.76
    ience
    -0.75
    żo
    -0.75
     Zuh
    -0.75
    tahan
    -0.75
    Commander
    -0.75
    Ą
    -0.74
    POSITIVE LOGITS
     apply
    1.00
     application
    0.99
    applying
    0.92
     applying
    0.91
     broadcast
    0.88
     applied
    0.87
    apply
    0.85
     chicken
    0.85
     broadcasting
    0.83
     INCORPOR
    0.83
    Activations Density 0.014%

    No Known Activations