© 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. 78921
    Prev
    Next
    INDEX
    Explanations

    geochemical element patterns

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

    terms related to geochemistry, geological elements, and earth science.

    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
    ジェクト
    -0.75
     estrutura
    -0.75
    cửa
    -0.75
    ೨
    -0.75
     BorderRadius
    -0.74
    amqp
    -0.74
    Struct
    -0.73
    failures
    -0.73
    nitten
    -0.73
     muối
    -0.72
    POSITIVE LOGITS
     enrichment
    1.00
    chemical
    0.98
     deple
    0.82
     geochemical
    0.81
     Chemical
    0.80
     enriquec
    0.80
     enrich
    0.79
     spider
    0.79
    Chemical
    0.77
     plots
    0.77
    Activations Density 0.026%

    No Known Activations