© 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. 20290
    Prev
    Next
    INDEX
    Explanations

    neuropathic and neuropathies

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

    The neuron activates for the word "neuropath" and its variations such as "neuropathic", "neuropathology", and "neuropathies" in medical or scientific contexts.

    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
    </h2>
    -2.56
     Saltar
    -2.48
    ⡪
    -2.47
    痦
    -2.47
    ⦊
    -2.47
    ⢓
    -2.39
    ௅
    -2.19
     повідом
    -2.11
     zimowe
    -2.11
     huit
    -2.08
    POSITIVE LOGITS
    垍
    3.56
    '
    3.09
    呖
    2.95
    薷
    2.95
    },
    2.94
     they
    2.89
    诹
    2.86
     ähnliche
    2.77
    蟜
    2.77
    ',
    2.75
    Activations Density 0.008%

    No Known Activations