© 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. 8540
    Prev
    Next
    INDEX
    Explanations

    alkene and related compounds

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

    chemical compounds and terminology related to organic chemistry, particularly focusing on alkenes/olefins and molecular structures.

    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
    ?
    -2.25
    er
    -1.99
    ve
    -1.92
    /
    -1.89
    va
    -1.70
    ”,
    -1.66
    icoot
    -1.66
    ”.
    -1.65
    for
    -1.62
    ds
    -1.61
    POSITIVE LOGITS
     zubehör
    1.93
    滹
    1.88
     quatrième
    1.82
     deuxième
    1.80
     bendera
    1.79
     wuß
    1.76
     boneka
    1.76
     totiž
    1.75
     our
    1.75
     gewi
    1.74
    Activations Density 0.091%

    No Known Activations