© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92303
    Prev
    Next
    INDEX
    Explanations

    geochemical anomalies

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

    scientific and technical content related to elements, minerals, and geological/environmental measurements.

    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
    ACK
    -0.83
    러한
    -0.77
     buckling
    -0.76
    olisme
    -0.73
    hynch
    -0.73
    illants
    -0.73
    upsi
    -0.72
    hagic
    -0.71
    <0xF1>
    -0.71
    besondere
    -0.70
    POSITIVE LOGITS
     sample
    0.91
     geochemical
    0.91
     anomalous
    0.86
     anomaly
    0.80
    异常
    0.77
     gold
    0.76
     attaque
    0.76
    ppb
    0.74
    ICP
    0.73
     siehe
    0.73
    Activations Density 0.014%

    No Known Activations