© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32602
    Prev
    Next
    INDEX
    Explanations

    carbon, water, oxygen, coal, marl

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

    chemical compounds and scientific terms like water, acid, alcohol, and various chemical elements.

    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
     awareness
    -0.85
     extending
    -0.81
     in
    -0.78
     all
    -0.76
    wise
    -0.74
    よー
    -0.73
     assess
    -0.72
    cão
    -0.72
     some
    -0.71
    ItemType
    -0.71
    POSITIVE LOGITS
     TPP
    0.82
    endio
    0.79
    듭
    0.79
     وفا
    0.78
    Hvor
    0.78
    laszt
    0.78
    inited
    0.77
     japonés
    0.77
     ARK
    0.76
    ƚ
    0.76
    Activations Density 0.037%

    No Known Activations