© 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. 23700
    Prev
    Next
    INDEX
    Explanations

    trace elements, metals, amines

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

    The neuron identifies the word "trace" and its variations in technical contexts, including software traces, chemical trace elements, and traceability in systems.

    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
    stale
    -0.96
    toare
    -0.89
     Verify
    -0.88
    已经有
    -0.87
     Rd
    -0.87
    unconfirmed
    -0.86
    рд
    -0.84
     fashioned
    -0.83
     Sheet
    -0.81
    🏷
    -0.81
    POSITIVE LOGITS
     Trace
    1.41
     Tracing
    1.29
    Trace
    1.27
     trace
    1.27
    trace
    1.23
     traced
    1.18
     AMOUNT
    1.12
     TRACE
    1.10
     amounts
    1.08
     tracing
    1.06
    Activations Density 0.009%

    No Known Activations