© 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. 68891
    Prev
    Next
    INDEX
    Explanations

    volatile organic compounds

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

    words related to volatile substances and vapors in scientific or chemical 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_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
    )]=
    -1.56
    渙
    -1.54
    ⫹
    -1.52
     姆
    -1.50
    uhnya
    -1.45
    neider
    -1.41
    __':
    -1.41
    FFE
    -1.38
     pediu
    -1.38
    criminator
    -1.36
    POSITIVE LOGITS
    Engl
    1.26
     Changes
    1.22
     tratta
    1.20
    \\
    1.20
    }
    1.20
    Mä
    1.15
    e
    1.13
    那位
    1.13
     trasforma
    1.13
    sed
    1.12
    Activations Density 0.071%

    No Known Activations