© 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. 31007
    Prev
    Next
    INDEX
    Explanations

    magneto, metabolism, metabolomics

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

    scientific terms related to magnetism, metabolism, and chemical processes, particularly words with prefixes like "magneto-" and "metabol-".

    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
    leder
    -0.74
     utils
    -0.72
    دي
    -0.71
    原子
    -0.71
     refineries
    -0.70
     định
    -0.69
    Geografi
    -0.69
    ón
    -0.69
    รับ
    -0.69
     Cotter
    -0.68
    POSITIVE LOGITS
    ?=
    0.72
    0.72
     ism
    0.72
    迫力
    0.71
    ism
    0.71
    יז
    0.71
    fled
    0.70
     BEL
    0.70
    heus
    0.70
    oples
    0.69
    Activations Density 0.065%

    No Known Activations