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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60538
    Prev
    Next
    INDEX
    Explanations

    seed and its qualities

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

    agricultural terms related to seeds, plants, and crop production.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds strongly to occurrences of the word “seed” (including seed-borne or seed-infection contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Appender
    -0.87
    UNES
    -0.83
    mson
    -0.78
     található
    -0.78
    PLAUSE
    -0.76
    Hdr
    -0.76
     Vegetarian
    -0.73
    Canon
    -0.73
    YPTO
    -0.72
    istö
    -0.72
    POSITIVE LOGITS
     seed
    1.66
     seeds
    1.22
     Seed
    1.15
    seed
    1.12
     multiplication
    1.09
     certified
    1.08
     purity
    1.04
    Seed
    1.02
     certification
    0.98
     quality
    0.97
    Activations Density 0.021%

    No Known Activations