© 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. 38765
    Prev
    Next
    INDEX
    Explanations

    CAS registry numbers or chemical names

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

    The neuron detects chemical or technical identifiers, particularly CAS (Chemical Abstracts Service) registry numbers.

    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
    '
    -3.73
     comanda
    -2.61
     However
    -2.61
    ;
    -2.55
    嫫
    -2.39
    section
    -2.22
    ти
    -2.20
    鹉
    -2.16
    榈
    -2.14
    是一款
    -2.06
    POSITIVE LOGITS
    e
    3.06
    al
    2.78
    ar
    2.66
    </strong>
    2.42
    u
    2.38
    6
    2.09
    F
    2.09
    愿望
    2.05
     impede
    2.03
    </sup>
    2.00
    Activations Density 0.004%

    No Known Activations