© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66631
    Prev
    Next
    INDEX
    Explanations

    residential apartment sale

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

    The neuron flags real‐estate development and marketing terms—especially property project names and construction/residential keywords.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     use
    -1.59
    !”
    -1.34
    цыі
    -1.32
    tième
    -1.31
     cuando
    -1.30
     பய
    -1.29
     homoto
    -1.27
     عندما
    -1.27
     learn
    -1.25
     advise
    -1.25
    POSITIVE LOGITS
     塗装
    1.30
    PropertyChanging
    1.26
    realpath
    1.24
    霾
    1.24
     forêts
    1.23
    ској
    1.23
    гают
    1.21
     montón
    1.19
     précédentes
    1.19
     oreille
    1.18
    Activations Density 0.048%

    No Known Activations