© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30139
    Prev
    Next
    INDEX
    Explanations

    home security and smart devices

    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
    Negative Logits
     RESPONS
    -0.80
     ALTER
    -0.73
     nfs
    -0.72
     worsened
    -0.72
     RestTemplate
    -0.72
    ✔️
    -0.71
    charts
    -0.69
     sank
    -0.67
    rierten
    -0.67
    之色
    -0.67
    POSITIVE LOGITS
     thermostat
    1.62
     smoke
    1.62
     Smoke
    1.40
     doorbell
    1.23
     thermo
    1.23
    smoke
    1.20
    Smoke
    1.13
     leak
    1.12
     door
    1.03
     Thermostat
    1.00
    Activations Density 0.031%

    No Known Activations