© 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. 57621
    Prev
    Next
    INDEX
    Explanations

    polyethylene glycol

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

    names of specific chemical compounds, materials, and scientific fields, especially terms like "polyethylene", "scholastic", "astronomy", "Booker" and "Foley".

    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
    u
    -3.22
    1
    -2.92
    2
    -2.72
    es
    -2.66
    r
    -2.64
    </h5>
    -2.59
    s
    -2.58
    d
    -2.56
    ଝ
    -2.53
    塒
    -2.50
    POSITIVE LOGITS
    </strong>
    3.00
    <td>
    2.58
    二月
    2.56
    íses
    2.55
    
    2.53
     That
    2.52
    ally
    2.45
     Мы
    2.38
    睺
    2.36
    着一
    2.31
    Activations Density 0.021%

    No Known Activations