© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110992
    Prev
    Next
    INDEX
    Explanations

    blocks, wedges, spacers, pads

    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
    苺
    -0.84
    NSData
    -0.83
     kandungan
    -0.76
    вление
    -0.75
     Лит
    -0.73
     anc
    -0.72
     mooring
    -0.69
    Holidays
    -0.69
    werty
    -0.69
     عج
    -0.69
    POSITIVE LOGITS
     blocks
    1.50
    垫
    1.45
     block
    1.40
     wedges
    1.38
     shim
    1.34
     wedge
    1.32
     placed
    1.30
    blocks
    1.28
    block
    1.24
     pads
    1.24
    Activations Density 0.037%

    No Known Activations