© 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. 10-GEMMASCOPE-RES-131K
    7. 15390
    Prev
    Next
    INDEX
    Explanations

    swelling and expansion

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

    words and phrases related to swelling, bloating, or expansion.

    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
    if
    -1.86
    re
    -1.59
    ah
    -1.50
    no
    -1.41
    th
    -1.37
     使っ
    -1.37
     kemudian
    -1.31
    9
    -1.27
    ne
    -1.25
    au
    -1.25
    POSITIVE LOGITS
    ományos
    1.59
     inflated
    1.59
    Karakter
    1.59
    Ꮠ
    1.58
     bloated
    1.56
     oyuncak
    1.44
    steuer
    1.43
    vestidos
    1.39
    schon
    1.38
     Franchise
    1.37
    Activations Density 0.081%

    No Known Activations