© 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. 118089
    Prev
    Next
    INDEX
    Explanations

    trees, logs, wood

    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
     trow
    -0.87
    urahan
    -0.81
    Snail
    -0.81
    teca
    -0.81
    vettes
    -0.78
    Spinach
    -0.77
     CIV
    -0.77
    OECD
    -0.76
     pebbles
    -0.76
     varför
    -0.75
    POSITIVE LOGITS
     trees
    2.31
     tree
    2.22
     logs
    2.11
     fallen
    1.88
     trunks
    1.67
    trees
    1.63
    tree
    1.62
     log
    1.56
     trunk
    1.56
     Trees
    1.53
    Activations Density 0.024%

    No Known Activations