© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107275
    Prev
    Next
    INDEX
    Explanations

    fruit and seeds

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

    botanical terms related to plant reproduction, focusing on seeds, fruits, berries, and flowering parts.

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

    The neuron is highly sensitive to scientific‐style biological nomenclature and quantitative descriptors—e.g. Latin species names and numeric measurements in plant/organism descriptions.

    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
     Buffer
    -0.88
    nologue
    -0.81
     câncer
    -0.79
    Cyfeiriadau
    -0.76
    レギュラー
    -0.73
     prestig
    -0.72
     移
    -0.71
     Strecken
    -0.71
     consente
    -0.71
    咁
    -0.70
    POSITIVE LOGITS
     seed
    1.84
     pods
    1.64
     seeds
    1.63
     Seeds
    1.45
    seed
    1.43
     capsule
    1.38
    Seed
    1.38
     capsules
    1.36
     pod
    1.34
     fruit
    1.33
    Activations Density 0.039%

    No Known Activations