© 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. 10-GEMMASCOPE-RES-131K
    7. 100901
    Prev
    Next
    INDEX
    Explanations

    mass spectrometer

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

    scientific references to mass spectrometry and related analytical chemistry techniques.

    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
    
    -1.51
    😑
    -1.48
    ля
    -1.47
    …”
    -1.38
    会的
    -1.36
     😂😂
    -1.36
    …]
    -1.36
    ine
    -1.35
    ты
    -1.34
    oną
    -1.34
    POSITIVE LOGITS
     until
    1.36
     become
    1.34
     \
    1.34
     of
    1.27
     diventare
    1.24
     devenus
    1.23
    лично
    1.20
    ommt
    1.20
    Dlaczego
    1.20
     like
    1.20
    Activations Density 0.086%

    No Known Activations