© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2516
    Prev
    Next
    INDEX
    Explanations

    wooden pieces

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

    The neuron activates on words naming physical materials or surfaces.

    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
     polystyrene
    0.61
     goma
    0.61
    unitas
    0.60
     mahogany
    0.59
    locationY
    0.59
    铜
    0.58
     деревя
    0.58
     drewn
    0.57
     сили
    0.56
     اخبار
    0.56
    POSITIVE LOGITS
    ாலான
    1.00
    製の
    0.99
     roofing
    0.82
     slabs
    0.79
    製
    0.78
     bodied
    0.75
     slab
    0.75
    ிலான
    0.74
     sheeting
    0.74
    খণ্ড
    0.73
    Activations Density 0.674%

    No Known Activations