© 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. 34-GEMMASCOPE-RES-131K
    7. 57262
    Prev
    Next
    INDEX
    Explanations

    porphyrin, dipole moment, aggregate

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

    chemical compounds and molecular structures in scientific papers.

    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_34/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
    сное
    -0.71
    GeneratedCode
    -0.71
    ذف
    -0.71
    网易
    -0.69
    نسي
    -0.68
     versteht
    -0.68
     consumer
    -0.67
     Talis
    -0.67
     during
    -0.67
     Regency
    -0.67
    POSITIVE LOGITS
    Aggregate
    0.94
    aggregate
    0.85
    BAND
    0.79
     Aggregate
    0.79
     Franck
    0.77
     Theor
    0.77
     練習
    0.75
    ткий
    0.75
    baut
    0.74
     перевоз
    0.72
    Activations Density 0.121%

    No Known Activations