© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10088
    Prev
    Next
    INDEX
    Explanations

    chicken pox, growing seedlings

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

    The neuron fires most strongly on mentions of NASA’s space‐based plant‐growth experiments (e.g. “NASA first developed this technique to grow plants in space”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dog
    0.91
     Dog
    0.81
     dogs
    0.79
     deer
    0.77
     DOG
    0.75
     Dogs
    0.72
    狗
    0.71
     wildlife
    0.70
     canine
    0.70
     hounds
    0.70
    POSITIVE LOGITS
    Cage
    1.04
    培养
    0.99
     Cage
    0.96
    cage
    0.94
    Indoor
    0.93
     cage
    0.91
     captivity
    0.91
    育て
    0.90
     پرورش
    0.88
     Aquarium
    0.85
    Activations Density 0.379%

    No Known Activations