© 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. 64030
    Prev
    Next
    INDEX
    Explanations

    electromagnetic spectrum regions

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

    text discussing wavelengths, frequencies, or spectral ranges in scientific contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ativit
    -0.82
    事務
    -0.77
    kowe
    -0.75
     havi
    -0.73
     стоя
    -0.72
    さんは
    -0.72
    ctez
    -0.72
    CIUDAD
    -0.71
    ค์
    -0.71
    éreo
    -0.71
    POSITIVE LOGITS
     infrared
    1.33
     ultraviolet
    1.33
     UV
    1.32
     microwave
    1.23
     infra
    1.16
     VHF
    1.13
     range
    1.11
     UHF
    1.11
    infrared
    1.11
     visible
    1.09
    Activations Density 0.089%

    No Known Activations