© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50312
    Prev
    Next
    INDEX
    Explanations

    wavelength of lasers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    phous
    -0.76
    ricts
    -0.75
     sobri
    -0.73
     řízení
    -0.72
    ступление
    -0.72
    竽
    -0.72
     fett
    -0.70
     bruin
    -0.70
    aide
    -0.69
    EIS
    -0.69
    POSITIVE LOGITS
     wavelength
    1.20
     wavelengths
    1.05
     around
    1.02
     operating
    0.98
     centro
    0.85
     Det
    0.83
     telecom
    0.80
     lasers
    0.79
     Center
    0.79
     tele
    0.79
    Activations Density 0.076%

    No Known Activations