© 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. 124060
    Prev
    Next
    INDEX
    Explanations

    neuro-optical inflammation

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

    The neuron detects hyphenated prefixes in scientific and technical terminology, particularly those used in medical, biological, and engineering 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
    獃
    -2.27
    䜣
    -2.20
    玙
    -2.17
    翾
    -2.08
    %;
    -2.08
     Of
    -2.02
     who
    -1.99
    钐
    -1.96
     "]";
    -1.93
    ].)
    -1.93
    POSITIVE LOGITS
    0
    2.39
    6
    1.95
     or
    1.83
     laajenta
    1.75
     elektrik
    1.71
     of
    1.59
    Unlike
    1.59
    Suka
    1.59
    〜〜
    1.57
    5
    1.57
    Activations Density 0.074%

    No Known Activations