© 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. 12676
    Prev
    Next
    INDEX
    Explanations

    cars

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

    The neuron activates on mentions of vehicles—especially the word “car” and its variants.

    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
     पैदल
    0.63
    かね
    0.55
    от
    0.54
     aboard
    0.54
    OCT
    0.53
    忍
    0.52
    ುತ್ತ
    0.52
    Otto
    0.52
    বুঝ
    0.52
    }^{
    0.51
    POSITIVE LOGITS
    ยนต์
    0.89
     parked
    0.88
     dealership
    0.76
    輌
    0.75
     dealerships
    0.74
    pool
    0.71
    pooling
    0.71
    চালক
    0.69
    actéristiques
    0.69
     মার্ক
    0.66
    Activations Density 0.272%

    No Known Activations