© 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. 57892
    Prev
    Next
    INDEX
    Explanations

    micrograms, nanograms, and similar units

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

    numerical measurements with scientific units, particularly concentrations expressed in units like μg/kg, mg/L, or ng/dL.

    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
     ppm
    -1.20
    ppm
    -0.95
    MeV
    -0.87
     MeV
    -0.79
     милли
    -0.78
    nhi
    -0.72
     milyon
    -0.72
    domaine
    -0.71
     million
    -0.71
     желу
    -0.71
    POSITIVE LOGITS
     ppt
    0.77
    țiunea
    0.74
    particle
    0.70
    стал
    0.68
    থা
    0.68
     nazwis
    0.67
     δυνα
    0.66
     Käse
    0.66
    vtk
    0.66
     Gibraltar
    0.65
    Activations Density 0.040%

    No Known Activations