© 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. 89946
    Prev
    Next
    INDEX
    Explanations

    larvae feeding

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

    This neuron activates for descriptions of organisms and their biological characteristics, particularly focusing on insects, bacteria, and other small organisms.

    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
     vair
    -0.71
     الو
    -0.69
     Fara
    -0.68
    epsfig
    -0.67
     permita
    -0.66
     enthalten
    -0.66
     Gegenstand
    -0.66
     marad
    -0.66
    合作
    -0.66
     CBT
    -0.66
    POSITIVE LOGITS
     feed
    4.22
     feeds
    3.88
     feeding
    3.78
    feed
    3.69
    feeding
    3.19
     Feed
    3.11
    Feed
    3.08
     Feeding
    3.05
    feeds
    3.02
    FEED
    3.00
    Activations Density 0.068%

    No Known Activations