© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99650
    Prev
    Next
    INDEX
    Explanations

    NIR infrared spectroscopy

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

    scientific or technical terms related to measurement, spectroscopy, and imaging technologies.

    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
    Erstellt
    -0.80
     frat
    -0.74
    ztály
    -0.73
     pecans
    -0.73
     Bernoulli
    -0.71
    PTC
    -0.71
     garam
    -0.70
     suprema
    -0.70
     rares
    -0.70
    みが
    -0.70
    POSITIVE LOGITS
     tissue
    1.04
     NIR
    1.02
     fluence
    0.96
     light
    0.94
     Tuch
    0.93
     opto
    0.92
     hemoglobin
    0.90
     absorption
    0.88
     contrasts
    0.86
     chrom
    0.85
    Activations Density 0.069%

    No Known Activations