© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93558
    Prev
    Next
    INDEX
    Explanations

    residential services and customers

    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
    墙壁
    -1.03
    Qur
    -1.02
     applau
    -0.98
     검색
    -0.97
     sonidos
    -0.96
     arreglos
    -0.94
    工作人员
    -0.93
    saat
    -0.93
     delightfully
    -0.92
    lerinin
    -0.91
    POSITIVE LOGITS
     homeowner
    1.54
     customers
    1.51
     customer
    1.42
     clients
    1.41
    客户
    1.36
     client
    1.35
     homeowners
    1.32
     residential
    1.27
     Residential
    1.17
     install
    1.13
    Activations Density 0.030%

    No Known Activations