© 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. 34-GEMMASCOPE-RES-131K
    7. 65304
    Prev
    Next
    INDEX
    Explanations

    plasma followed by scientific descriptors

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

    The word "plasma" at the beginning of scientific or technical 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
     マンガ
    -0.90
    enee
    -0.86
     cyn
    -0.81
     Trag
    -0.79
     Hereford
    -0.76
     Dign
    -0.76
     nejs
    -0.76
     panda
    -0.74
    之战
    -0.73
     يو
    -0.73
    POSITIVE LOGITS
     Plasma
    1.22
    Donations
    1.12
    pher
    1.05
    Plasma
    1.02
     membrane
    1.01
    dash
    1.00
    Ainsi
    0.94
    plasma
    0.84
     Membrane
    0.83
    blasts
    0.83
    Activations Density 0.038%

    No Known Activations