© 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. 13612
    Prev
    Next
    INDEX
    Explanations

    call or email support

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

    The neuron activates on mentions of submitting or following up on support requests (e.g. opening tickets, clicking password‐reset links, contacting support).

    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
    ్యాన్ని
    0.57
     PHOT
    0.55
    ORK
    0.53
     muslin
    0.52
     rétrécies
    0.51
    াদী
    0.50
     égales
    0.50
    
    0.50
     levy
    0.49
     ड्राई
    0.49
    POSITIVE LOGITS
     Customer
    1.80
     customer
    1.70
    Customer
    1.65
     Support
    1.61
    customer
    1.59
     support
    1.53
    客服
    1.53
    support
    1.52
    Support
    1.52
    CUSTOMER
    1.38
    Activations Density 0.413%

    No Known Activations