© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113289
    Prev
    Next
    INDEX
    Explanations

    transmittance, conductance, reflectance

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

    The neuron flags technical scientific measurement nouns that name physical properties (e.g. transmittance, reflectance, conductance, conductivity).

    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
    ógicos
    -2.77
    يل
    -2.22
    ين
    -2.14
    ógica
    -2.13
    quelize
    -2.13
     décider
    -2.09
     всем
    -1.98
    v
    -1.98
     умира
    -1.90
    larak
    -1.88
    POSITIVE LOGITS
     of
    2.34
    -
    2.02
    ikkert
    1.95
     incluidos
    1.84
    dersfield
    1.81
     "
    1.81
    壷
    1.81
    ichtete
    1.80
    関する
    1.79
     娘
    1.73
    Activations Density 0.020%

    No Known Activations