© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10505
    Prev
    Next
    INDEX
    Explanations

    progression of disease

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

    The neuron detects phrases involving "progression of" when discussing disease advancement, research, or processes.

    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
    镦
    -3.20
    埽
    -2.41
    }
    -2.41
    ῎
    -2.34
     Invoice
    -2.28
    猻
    -2.28
    смотра
    -2.20
    不错的
    -2.13
    ︕
    -2.11
    s
    -2.09
    POSITIVE LOGITS
    ’
    3.16
     Angebote
    2.52
    $,
    2.42
     selben
    2.34
     viele
    2.28
    怎么能
    2.27
     Importantly
    2.23
    婓
    2.23
     After
    2.20
    ↵
    2.13
    Activations Density 0.007%

    No Known Activations