© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83925
    Prev
    Next
    INDEX
    Explanations

    real estate broker license

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     bloqueo
    -0.79
    certification
    -0.78
     chá
    -0.77
    mors
    -0.75
    ⓖ
    -0.75
    Certification
    -0.74
    piec
    -0.73
     chercher
    -0.71
     сту
    -0.70
    ochim
    -0.70
    POSITIVE LOGITS
     license
    1.32
     broker
    1.26
    license
    1.23
    License
    1.21
     licensees
    1.19
     licensing
    1.16
     salesperson
    1.14
     licensed
    1.13
     Broker
    1.12
     licensee
    1.11
    Activations Density 0.009%

    No Known Activations