© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1330
    Prev
    Next
    INDEX
    Explanations

    5-FU therapy

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

    medical/pharmaceutical names and chemical compounds in scientific literature, particularly interleukins and drugs.

    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
    —–
    -1.57
    는
    -1.46
    شخص
    -1.45
    ࠬ
    -1.42
    ším
    -1.42
     ۴
    -1.41
    pping
    -1.40
     hampered
    -1.36
    деля
    -1.36
    точно
    -1.36
    POSITIVE LOGITS
    }$.
    1.57
    only
    1.52
    }$,
    1.51
    ↵↵↵
    1.48
     only
    1.44
    inephrine
    1.39
    ."
    1.38
    Nội
    1.38
     ones
    1.34
     voor
    1.34
    Activations Density 0.039%

    No Known Activations