© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 190797
    Prev
    Next
    INDEX
    Explanations

    polarization of light

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    喍
    0.42
    Spell
    0.41
    ˃
    0.39
    spell
    0.39
    रासत
    0.38
    Dn
    0.38
    䄸
    0.38
     "',
    0.37
     barcelona
    0.37
     spell
    0.37
    POSITIVE LOGITS
     polarization
    1.70
     polarized
    1.64
     Polarization
    1.64
     polarised
    1.50
     polarisation
    1.49
     polarizing
    1.37
    polarized
    1.34
     polarizer
    1.32
     polar
    1.24
     Polar
    1.23
    Activations Density 0.011%

    No Known Activations