© 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. 34-GEMMASCOPE-RES-131K
    7. 48559
    Prev
    Next
    INDEX
    Explanations

    polarization optics

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

    The neuron strongly activates on technical terms related to polarization analysis in optics (e.g. Mueller and Stokes formalisms).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     polymerase
    -0.82
     porém
    -0.75
     DUAL
    -0.75
    क्रम
    -0.73
     isotopes
    -0.73
    JsonNode
    -0.73
     bVar
    -0.71
     polarized
    -0.71
    dual
    -0.70
     Movers
    -0.70
    POSITIVE LOGITS
     sunglasses
    0.82
     Максима
    0.81
     windshield
    0.80
    preferences
    0.80
     اضط
    0.77
     fön
    0.77
     Maximum
    0.74
    Bahnhof
    0.74
     discriminating
    0.74
    ።
    0.74
    Activations Density 0.020%

    No Known Activations