© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75631
    Prev
    Next
    INDEX
    Explanations

    relating to contracts and sales

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

    The neuron fires on terminology related to real estate and property–investment (e.g. “real,” “estate,” “acquisition,” “sale,” “assets,” “portfolios,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     verantwort
    -0.99
     wasn
    -0.98
     доби
    -0.96
     didn
    -0.95
     aren
    -0.91
     блюдо
    -0.89
     isn
    -0.88
     pietra
    -0.87
     फ़
    -0.84
    ńskiej
    -0.84
    POSITIVE LOGITS
    𓂂
    1.21
     thereto
    1.17
     pursuant
    1.17
    THRESHOLD
    1.17
     thereunder
    1.16
    Whilst
    1.16
    ᾽
    1.09
    וּ
    1.08
     mencionar
    1.07
     EUR
    1.05
    Activations Density 0.015%

    No Known Activations