© 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. 6434
    Prev
    Next
    INDEX
    Explanations

    includes explanations

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

    The neuron fires strongly on descriptive real‐estate or accommodation listing language (e.g. room/feature counts, amenities, and property details).

    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
    成分
    0.60
     Ereign
    0.58
    <unused60>
    0.57
     未
    0.56
    命
    0.56
    NG
    0.56
     म्हणूनच
    0.56
    因
    0.56
     reacted
    0.55
     성공
    0.55
    POSITIVE LOGITS
     restrooms
    1.09
     bathrooms
    0.98
     piscina
    0.98
     karaoke
    0.96
     landscaped
    0.96
     toilets
    0.95
     cafeteria
    0.95
     ampio
    0.94
     playgrounds
    0.94
     terraza
    0.93
    Activations Density 0.555%

    No Known Activations