Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8095
    Prev
    Next
    INDEX
    Explanations

    blinds, shutters, curtains, shades

    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
    Assertions
    -0.85
     beacon
    -0.85
     Accelerated
    -0.75
     サポート
    -0.73
     Basket
    -0.73
     SOAP
    -0.73
    SSON
    -0.71
     jacke
    -0.70
    Statics
    -0.70
     Bubbles
    -0.70
    POSITIVE LOGITS
     blinds
    3.08
     shutters
    2.59
     shades
    2.27
     curtains
    2.19
     Blinds
    2.02
     blind
    1.94
     shutter
    1.73
     shade
    1.60
    blind
    1.54
     roller
    1.52
    Activations Density 0.016%

    No Known Activations