© 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. 10-GEMMASCOPE-RES-131K
    7. 39253
    Prev
    Next
    INDEX
    Explanations

    scientific units with powers

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

    scientific units of measurement including cm, km, s, mol, g, and min with superscript notation.

    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_10/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
    ',
    -1.81
     undeniably
    -1.77
     (
    -1.76
     unquestionably
    -1.75
     incessant
    -1.73
     oftentimes
    -1.67
     neatly
    -1.65
     perpetually
    -1.63
    Even
    -1.63
     هستند
    -1.63
    POSITIVE LOGITS
    튿
    2.06
    
    1.97
    without
    1.83
    觚
    1.82
    搋
    1.78
    ONAUT
    1.74
    傒
    1.73
     maravill
    1.72
    tored
    1.70
    盌
    1.70
    Activations Density 0.001%

    No Known Activations