© 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. 10-GEMMASCOPE-RES-131K
    7. 123578
    Prev
    Next
    INDEX
    Explanations

    scientific compounds of matter

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

    The neuron detects the term "matter" especially when it appears in scientific contexts like "particulate matter," "organic matter," "gray matter," or "Dark Matter."

    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_10/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
     kesi
    -2.59
     ſame
    -2.53
     perak
    -2.41
    }$
    -2.39
     seleccionadas
    -2.36
     teater
    -2.23
     baju
    -2.23
     udang
    -2.22
     distrik
    -2.17
     polisi
    -2.14
    POSITIVE LOGITS
     It
    2.55
     neuen
    2.38
     to
    2.36
    </strong>
    2.34
    </em>
    2.27
     Also
    2.22
    </h3>
    2.20
     When
    2.19
    ),
    2.16
     That
    2.16
    Activations Density 0.009%

    No Known Activations