© 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. 12798
    Prev
    Next
    INDEX
    Explanations

    The main thing this neuron does is find mentions of moving or packing in the context of relocation services.

    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
    耕
    0.64
     Cep
    0.59
    ஷா
    0.56
     Galer
    0.53
    醸
    0.53
     cep
    0.51
     arable
    0.51
     recharging
    0.50
     crus
    0.50
     कैफ
    0.50
    POSITIVE LOGITS
     packing
    1.54
     movers
    1.47
    packing
    1.45
     packers
    1.40
     Packing
    1.38
    Packing
    1.36
    搬
    1.35
     unpacking
    1.33
    行李
    1.33
     suitcases
    1.23
    Activations Density 0.420%

    No Known Activations