© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116427
    Prev
    Next
    INDEX
    Explanations

    surface deposit formation

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron identifies references to deposits, buildup, or accumulations on surfaces, particularly in technical and scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     punctures
    -0.79
     پوست
    -0.78
     DRAIN
    -0.77
    詔
    -0.76
    dames
    -0.74
    ıç
    -0.73
     TIT
    -0.72
    pondi
    -0.72
     encre
    -0.72
     antivirus
    -0.71
    POSITIVE LOGITS
     deposits
    2.86
     deposit
    2.47
     buildup
    2.45
     deposition
    2.27
     deposited
    2.11
    deposit
    2.05
     Deposits
    2.03
     build
    2.02
     Deposit
    1.94
    Deposits
    1.91
    Activations Density 0.076%

    No Known Activations