© 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. 10-GEMMASCOPE-RES-131K
    7. 103930
    Prev
    Next
    INDEX
    Explanations

    pancreatic cancer and islets

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

    proper nouns and technical terms related to biology, law, or computing.

    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_10/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
    镭
    -2.81
    薤
    -2.81
    崛
    -2.75
    觏
    -2.66
    缡
    -2.66
     ethereal
    -2.58
     psychedelic
    -2.56
    ſelves
    -2.56
     empathetic
    -2.55
    最后由
    -2.55
    POSITIVE LOGITS
    1
    4.09
    2
    3.08
    0
    2.97
    7
    2.92
    3
    2.77
     reagiert
    2.69
    4
    2.61
    8
    2.52
    -
    2.50
    5
    2.48
    Activations Density 0.030%

    No Known Activations