© 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. 24-GEMMASCOPE-2-RES-16K
    7. 14795
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to wording characteristic of real-estate listings and property-for-sale advertisements.

    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_24_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
     it
    0.41
     keel
    0.41
     [
    0.40
     that
    0.38
     the
    0.36
     That
    0.35
     ĝi
    0.34
    <em>
    0.32
     WITH
    0.32
     hydrochloride
    0.32
    POSITIVE LOGITS
    様々な
    0.59
     다양한
    0.53
     العديد
    0.51
     विभिन्न
    0.46
     alcune
    0.46
     বিভিন্ন
    0.46
     여러
    0.45
     различных
    0.44
    有哪些
    0.44
     તેમજ
    0.43
    Activations Density 0.668%

    No Known Activations