© 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. 7772
    Prev
    Next
    INDEX
    Explanations

    butyl compounds

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

    technical terms related to chemistry and programming, particularly in document formatting such as table lines, chemical compounds, and code syntax.

    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
     Meksiko
    -2.34
     mobilen
    -2.19
    Ꭽ
    -2.14
    isième
    -2.13
     praktis
    -2.05
    要
    -2.03
     Meksi
    -2.00
    )」
    -1.96
    வை
    -1.94
     \
    -1.91
    POSITIVE LOGITS
    縠
    2.63
    甞
    2.30
    \
    2.23
    磲
    2.19
    ühnen
    2.13
    垻
    2.11
     importación
    2.11
    的车
    2.05
    ൎ
    1.99
     mehrfach
    1.98
    Activations Density 0.001%

    No Known Activations