© 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. 54075
    Prev
    Next
    INDEX
    Explanations

    glass containers

    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
     dérou
    -0.69
     straws
    -0.69
     spong
    -0.67
     płat
    -0.67
     napkins
    -0.67
    ัต
    -0.67
     incrust
    -0.66
     brooms
    -0.66
    Propor
    -0.65
     tapis
    -0.65
    POSITIVE LOGITS
     jars
    2.44
     jar
    2.13
     glass
    2.08
     bottles
    1.95
     bottle
    1.87
     Jars
    1.64
    glass
    1.63
    瓶
    1.58
    jar
    1.57
     Jar
    1.54
    Activations Density 0.023%

    No Known Activations