© 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. 8022
    Prev
    Next
    INDEX
    Explanations

    sulf compounds

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

    chemical compounds with sulfur, particularly words beginning with "sulf".

    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
    ’;
    -2.52
     is
    -2.48
    蔔
    -2.45
     ”
    -2.38
     Now
    -2.25
    AdvEx
    -2.25
    ’.
    -2.19
     Whether
    -2.17
     ‘’
    -2.17
    杁
    -2.16
    POSITIVE LOGITS
    }$
    2.64
    鋱
    2.53
    ]
    2.34
    횃
    2.34
    ⌵
    2.33
    ه
    2.16
     {
    2.08
    岜
    2.05
    m
    2.05
     και
    2.05
    Activations Density 0.010%

    No Known Activations