© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34749
    Prev
    Next
    INDEX
    Explanations

    housing market prices

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

    The neuron is tuned to detect real-estate market terminology—especially mentions of “market,” “prices,” and related property-pricing words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cucchiai
    -1.47
     grasas
    -1.39
    werden
    -1.39
     навсегда
    -1.38
     Bewußt
    -1.34
    ῷ
    -1.34
     zufried
    -1.32
    assigned
    -1.31
     otak
    -1.30
    цыі
    -1.30
    POSITIVE LOGITS
     market
    1.67
     in
    1.58
     prices
    1.55
    ﻷ
    1.46
     price
    1.45
     investors
    1.35
    снимок
    1.29
    緩
    1.28
    breviations
    1.26
     Índice
    1.25
    Activations Density 0.030%

    No Known Activations