© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13034
    Prev
    Next
    INDEX
    Explanations

    optics physics

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     क्वालीफ
    0.53
     Syllabus
    0.53
    ഹൃ
    0.53
     ละ
    0.52
    寿命
    0.52
    ຟ
    0.51
     piş
    0.50
    芽
    0.49
     रिवीजन
    0.49
     sacked
    0.49
    POSITIVE LOGITS
     permittivity
    1.03
     dielectric
    0.96
     refractive
    0.91
     resonances
    0.88
     waveguide
    0.87
     refracting
    0.86
     waveguides
    0.86
     resonators
    0.84
     Brewster
    0.79
     refraction
    0.78
    Activations Density 0.033%

    No Known Activations