© 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. 10-GEMMASCOPE-RES-131K
    7. 103809
    Prev
    Next
    INDEX
    Explanations

    quantum dots or nanoparticles

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

    nanoscale structures like quantum dots, nanoparticles, and nanocrystals.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to mentions of quantum dot(s) or closely related semiconductor nanocrystals.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ecstatic
    -1.59
    挈
    -1.51
    着一个
    -1.49
     отношению
    -1.49
    on
    -1.48
    ebly
    -1.47
    itary
    -1.47
     billeder
    -1.45
    ra
    -1.39
     two
    -1.38
    POSITIVE LOGITS
     such
    1.66
     comuniques
    1.63
     小物
    1.56
     serão
    1.55
     are
    1.51
     \
    1.49
    hidup
    1.48
     the
    1.45
    jawab
    1.45
    carian
    1.41
    Activations Density 0.058%

    No Known Activations