© 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. 7079
    Prev
    Next
    INDEX
    Explanations

    **Injections and dependencies**

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

    This neuron strongly activates on the word “Listing,” i.e. headings that introduce a real‐estate property listing.

    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
    ıları
    0.79
    l
    0.77
     nekoliko
    0.73
    нії
    0.71
    ਆਂ
    0.70
    nYou
    0.70
    enerbah
    0.70
     đâu
    0.68
     няколко
    0.68
    kick
    0.68
    POSITIVE LOGITS
    諡
    0.80
     deformations
    0.78
     lotions
    0.75
     beasts
    0.73
     interventions
    0.72
     endowments
    0.72
     ecologically
    0.71
     levies
    0.71
     quím
    0.71
    rechts
    0.71
    Activations Density 0.001%

    No Known Activations